WO2023070381A1

WO2023070381A1 - Method and apparatus for deploying movable base station

Info

Publication number: WO2023070381A1
Application number: PCT/CN2021/126771
Authority: WO
Inventors: Zhiqiang Qi; Jingya Li; Xingqin LIN
Original assignee: Telefonaktiebolaget LM Ericsson AB
Current assignee: Telefonaktiebolaget LM Ericsson AB
Priority date: 2021-10-27
Filing date: 2021-10-27
Publication date: 2023-05-04
Anticipated expiration: 2024-04-27

Abstract

Embodiments of the present disclosure provide methods and apparatus for deploying movable base station. The method comprises: collecting (S102), by a data collection module, data about measurements and/or performance metrics relating to at least one terminal device to be served by at least one movable base station; determining (S104), by a model inference module, configuration for deploying the at least one movable base station, based on at least part of the collected data; actuating (S106), by an actor module, the at least one movable base station, based on at least the determined configuration. The determined configuration optimizes at least one of the performances metrics at the at least one terminal device, which may be better than performances metrics when the at least one terminal device is served by the network node. Therefore, a proper decision on the deployment and configuration of the movable base station may be made.

Description

METHOD AND APPARATUS FOR DEPLOYING MOVABLE BASE STATION

TECHNICAL FIELD

The present disclosure relates generally to the technology of wireless communication, and in particular, to a method and an apparatus for deploying movable base station.

BACKGROUND

This section introduces aspects that may facilitate better understanding of the present disclosure. Accordingly, the statements of this section are to be read in this light and are not to be understood as admissions about what is in the prior art or what is not in the prior art.

In wireless communication networks, multiple relay nodes, e.g., integrated access and backhaul (IAB) nodes, can be used to extend, enhance, or even re-establish the network connectivity and/or quality of service (QoS) over a geographical area of interest (e.g., urban areas with high demands on capacity, disaster-struck areas where first-responder communication is critical) . These networks may be referred to as relay-assisted networks.

A relay-assisted network can consist of multiple relay nodes and the system architecture can be configured in a flexible and scalable way via multi-hop wireless backhauling, using the same or different frequency bands for access and backhaul.

For example, in a disaster area where there is no macro coverage or the original serving macro-BS breaks down, a movable base station can be set up to provide mission critical communications to first responders.

As the movable base station may be connected to the core network using wireless backhaul, it is important to ensure good quality of both the backhaul and access links when performing this system optimization. In addition, the limitations on movable base station’s altitude, operation time, antenna capabilities and transmit power also put additional constraints on the optimization problem. Furthermore, the optimal solution depends on many factors like network traffic load distribution, QoS requirements, UE movements, transmit power and antenna settings at the nearby on-ground BSs of the movable base station, etc.

Therefore, it is critical to find applicable manner to deploy such movable base stations.

SUMMARY

This summary is provided to introduce a selection of concepts in a simplified form that are further described below in the detailed description. This summary is not intended to identify key features or essential features of the claimed subject matter, nor is it intended to be used to limit the scope of the claimed subject matter.

Certain aspects of the present disclosure and their embodiments may provide solutions to these or other challenges. There are, proposed herein, various embodiments which address one or more of the issues disclosed herein. Specific method and apparatus for deploying movable base station may be provided.

A first aspect of the present disclosure provides a computer implemented method for deploying at least one movable base station to serve at least one terminal device in a communication network. The at least one terminal device may be served either by a network node or served through the at least one movable base station. The at least one movable base station may have a wireless backhaul link communicating with the network node functioning as a donor base station. The method may comprise: collecting, by a data collection module, data about measurements and/or performance metrics relating to the at least one terminal device to be served by at least one movable base station; determining, by a model inference module, configuration for deploying the at least one movable base station, based on at least part of the collected data; and actuating, by an actor module, the at least one movable base station, based on at least the determined configuration. The determined configuration may optimize at least one of the performances metrics at the at least one terminal device, and by using the determined configuration, the at least one of the performances metrics may be better when the at least one terminal device is served by the movable base station comparing to when the at least one terminal device is served by the network node.

In embodiments of the present disclosure, the data collection module is arranged at network side, and/or the data collection module is arranged near a source of the data.

In embodiments of the present disclosure, the data collection module is further configured to receive and apply feedback from the model inference module and/or the actor module, and/or a central server; and the feedback includes deployment strategy and/or suggested configuration based on algorithm prediction, and/or a global learning model. The central server may be located at the donor base station or a cloud.

In embodiments of the present disclosure, the deployment strategy and/or suggested configuration includes access antenna configuration, backhaul antenna configuration, backhaul routing path configuration, transmit power, 3-D location, and/or rotation/orientation of the at least one movable base station to serve the at least one terminal device.

In embodiments of the present disclosure, the collecting data is triggered by the donor base station for the at least one movable base station after the at least one movable base station completed a network integration procedure; or the collecting data is triggered after detecting a mobility event of the at least one movable base station; or the collecting data is triggered by the at least one movable base station, via a broadcasting message and/or a unicasting message and/or a multicasting message.

In embodiments of the present disclosure, the collected data comprises at least one of: load situation and/or resource utilization of the communication network; geographic information of area to be served; information about antenna tilting, and/or transmit power of a macro base station supporting or close to the at least one movable base station; applied configuration for the at least one movable base station, including electrical/mechanical antenna tilting, rotation, 3D location, transmit power; performance metrics relating to the applied configuration for the at least one movable base station, including statistics of the throughput, SINR, and drop rate of all connected users or a specific group of connected users for both DL and UL; link quality for a backhaul relating to the at least one movable base station; identity or location of the donor base station, number of wireless hops; and/or user information including labels to distinguish different types of terminal devices or services, statistics about proportion of the different types of terminal devices or services served by the at least one movable base station, mobility information of the at least one terminal device.

In embodiments of the present disclosure, the collected data is divided into two sub-sets as training data and inference data; the training data is inputted to a model training module; and the inference data is inputted to the model inference module.

In embodiments of the present disclosure, the method further comprises: training and updating a model used by the model inference module, by the model training module, based on at least the training data, and/or feedback from the model inference module.

In embodiments of the present disclosure, the model used by the model inference module is trained via an artificial intelligence/machine learning algorithm.

In embodiments of the present disclosure, the model inference module may determine the configuration, by inputting a part of the collected data to the model and obtaining an output from the model. The model inference module may output the configuration to the model training module as feedback.

In embodiments of the present disclosure, the data collection module, the model inference module, and the actor module are integrated in a movable base station of the at least one movable base station, or in an edge-cloud, or the donor base station for supporting the at least one movable base station; or the data collection module, the model inference module, and the actor module are distributed in more than one base station, including movable base station and/or static base station.

In embodiments of the present disclosure, a target movable base station in the at least one movable base station is connected to the donor base station via single-hop wireless backhauling. The target movable base station is operative for: collecting the data, via data reports from the at least one terminal device, and/or the donor base station, and/or a set of other selected base stations; training a model used by the model inference module, based on at least part of the collected data; generating the configuration for deploying the target movable base station, based on at least part of the collected data; actuating the target movable base station, based on at least the configuration; and feedbacking the configuration to the donor base station, and/or the set of other selected base stations.

In embodiments of the present disclosure, the data reports are triggered by the donor base station, or the target movable base station.

In embodiments of the present disclosure, a target movable base station in the at least one movable base station is connected to the donor base station via single-hop wireless backhauling. The donor base station is operative for: collecting the data, via data reports from the at least one terminal device, and/or the target movable base station, and/or a set of other selected base stations; training a model used by the model inference module, based on at least part of the collected data; generating the configuration for deploying the target movable base station, based on at least part of the collected data; and feedbacking the configuration to the target movable base station, and/or the set of other selected base stations. The target movable base station is operative for: collecting and transmitting data to the donor base station; and taking action, based on the configuration.

In embodiments of the present disclosure, a target movable base station in the at least one movable base station is connected to the donor base station via single-hop wireless backhauling. The donor base station is operative for: collecting the data, via data reports from the at least one terminal device, and/or the target movable base station, and/or a set of other selected base stations; training a model used by the model inference module, based on at least part of the collected data; transmitting, to the target movable base station, at least part of the collected data, and/or update for the model; cooperating with the target movable base station for generating the configuration for deploying the target movable base station, based on at least part of the collected data; and feedbacking the configuration to the target movable base station, and/or the set of other selected base stations. The target movable base station is operative for: collecting and transmitting data to the donor base station; receiving, from the donor base station, at least part of the collected data, and/or update for the model; cooperating with the donor base station for generating the configuration for deploying the target movable base station, based on at least part of the collected data; taking action, based on the configuration; and feedbacking the configuration to the donor base station, and/or the set of other selected base stations.

In embodiments of the present disclosure, a target movable base station in the at least one movable base station is connected to the donor base station via multi-hop wireless backhauling. The multi-hop wireless backhauling comprises at least one intermediate movable base station. The target movable base station is operative for: collecting the data, via data reports from the at least one terminal device, and/or at least one intermediate movable base station, and/or the donor base station, and/or a set of other selected base stations; training a model used by the model inference module, based on at least part of the collected data; cooperating with the at least one intermediate movable base station for generating the configuration for deploying the target movable base station, based on at least part of the collected data and feedback from the at least one intermediate movable base station; taking action, based on the configuration; and feedbacking the configuration to the at least one intermediate movable base station, and/or the donor base station, and/or a set of other selected base stations. The at least one intermediate movable base station is operative for: cooperating with the target movable base station, and/or other intermediate movable base stations, for generating another configuration for deploying the at least one intermediate movable base station, based on at least part of the collected data and feedback from the target movable base station; feedbacking another configuration to the donor base station, and/or the set of other selected base stations.

In embodiments of the present disclosure, the donor base station or the target movable base station is further operative for: triggering further data reports for updating the model used by the model inference module.

In embodiments of the present disclosure, the donor base station is further operative for: aggregating feedback from each of the at least one movable base station; and updating a model hosted in each of the at least one movable base station.

In embodiments of the present disclosure, updating the model is triggered by the donor base station, or the at least one movable base station.

In embodiments of the present disclosure, the at least one terminal device comprises at least one mission critical users; and/or the at least one movable base station comprises at least one unmanned aerial vehicle base station, UAV-BS.

A second aspect of the present disclosure provides an apparatus for deploying movable base station in a communication network. The apparatus may comprise: at least one processor; and at least one memory. The at least one memory contains instructions executable by the at least one processor. The apparatus is operative for: collecting, by a data collection module, data about measurements and/or performance metrics relating to at least one terminal device to be served by at least one movable base station; generating, by a model inference module, configuration for deploying the at least one movable base station, based on at least part of the collected data; actuating, by an actor module, the at least one movable base station, based on at least the configuration.

In embodiments of the present disclosure, the apparatus is further operative to perform the method according to any of embodiments of the first aspect.

A third aspect of the present disclosure provides a computer-readable storage medium storing instructions which when executed by at least one processor, cause the at least one processor to perform the method according to any of embodiments of the first aspect.

A fourth aspect of the present disclosure provides an apparatus for deploying at least one movable base station to serve at least one terminal device in a communication network. The at least one terminal device is served either by a network node or served through the at least one movable base station which has a wireless backhaul link communicating with the network node functioning as a donor base station. The apparatus may comprise: a data collection module, configured to collect data about measurements and/or performance metrics relating to the at least one terminal device to be served by at least one movable base station; a model inference module, configured to determine configuration for deploying the at least one movable base station, based on at least part of the collected data; an actor module, configured to actuate the at least one movable base station, based on at least the determined configuration. The determined configuration optimizes at least one of the performances metrics at the at least one terminal device, and by using the determined configuration, the at least one of the performances metrics is better when the at least one terminal device is served by the movable base station comparing to when the at least one terminal device is served by the network node.

Embodiments herein afford many advantages. According to embodiments of the present disclosure, the proposed procedure and frameworks can enable data collection from different network entities (e.g., BS, IAB nodes, cloud) , movable base station (such as UAV-BSs) and UEs. They also enable using the collected data for ML or other optimization algorithms to solve the complicated system optimization problem, and thereby making a proper decision on the deployment and configuration of the movable base station (such as UAV-BSs) .

BRIEF DESCRIPTION OF DRAWINGS

The above and other aspects, features, and benefits of various embodiments of the present disclosure will become more fully apparent, by way of example, from the following detailed description with reference to the accompanying drawings, in which like reference numerals or letters are used to designate like or equivalent elements. The drawings are illustrated for facilitating better understanding of the embodiments of the disclosure and not necessarily drawn to scale, in which:

FIG. 1 is a reference diagram for an IAB-architectures.

FIG. 2 is a diagram showing baseline control plane (CP) Protocol stack for IAB in Rel-16.

FIG. 3 is a diagram illustrating an example use case in public safety disaster recovery.

FIG. 4 is a diagram showing a functional framework for RAN Intelligence.

FIG. 5 is a flow chart showing a method for deploying movable base station in a communication network, according to embodiments of the present disclosure.

FIG. 6 is a diagram showing an example of UAV-BS assisted wireless communications.

FIG. 7 is a diagram showing a signaling procedure for example 1.

FIG. 8 is a diagram showing a signaling procedure for example 2.

FIG. 9 is a diagram showing a signaling procedure for example 3.

FIG. 10 is a diagram showing a signaling procedure for example 4.

FIG. 11 is a diagram showing a signaling procedure for example 5.

FIG. 12 is a diagram showing a signaling procedure for example 6.

FIG. 13 is a diagram showing a signaling procedure for example 7.

FIG. 14 is a diagram showing a signaling procedure for example 8.

FIG. 15 is a diagram showing a signaling procedure for example 9.

FIG. 16 is a diagram showing a signaling procedure for example 10.

FIG. 17 is a diagram showing a signaling procedure for example 11.

FIG. 18 is a diagram showing a signaling procedure for example 12.

FIG. 19 is a diagram showing an exemplary structure of a proposed optimization-based framework.

FIG. 20 is a diagram illustrating an example of UAV-BS assisted network deployment using IAB.

FIG. 21 is a diagram showing a framework and signaling procedure in this embodiment.

FIG. 22 (a) is a block diagram showing exemplary apparatuses suitable for perform the method according to embodiments of the disclosure.

FIG. 22 (b) is a block diagram showing an apparatus/computer readable storage medium, according to embodiments of the present disclosure.

FIG. 23 is a schematic showing units for the exemplary apparatuses, according to embodiments of the present disclosure.

FIG. 24 is a schematic showing a wireless network in accordance with some embodiments.

FIG. 25 is a schematic showing a user equipment in accordance with some embodiments.

FIG. 26 is a schematic showing a virtualization environment in accordance with some embodiments.

FIG. 27 is a schematic showing a telecommunication network connected via an intermediate network to a host computer in accordance with some embodiments.

FIG. 28 is a schematic showing a host computer communicating via a base station with a user equipment over a partially wireless connection in accordance with some embodiments.

FIG. 29 is a schematic showing methods implemented in a communication system including a host computer, a base station and a user equipment in accordance with some embodiments.

FIG. 30 is a schematic showing methods implemented in a communication system including a host computer, a base station and a user equipment in accordance with some embodiments.

FIG. 31 is a schematic showing methods implemented in a communication system including a host computer, a base station and a user equipment in accordance with some embodiments.

FIG. 32 is a schematic showing methods implemented in a communication system including a host computer, a base station and a user equipment in accordance with some embodiments.

DETAILED DESCRIPTION

The embodiments of the present disclosure are described in detail with reference to the accompanying drawings. It should be understood that these embodiments are discussed only for the purpose of enabling those skilled persons in the art to better understand and thus implement the present disclosure, rather than suggesting any limitations on the scope of the present disclosure. Reference throughout this specification to features, advantages, or similar language does not imply that all of the features and advantages that may be realized with the present disclosure should be or are in any single embodiment of the disclosure. Rather, language referring to the features and advantages is understood to mean that a specific feature, advantage, or characteristic described in connection with an embodiment is included in at least one embodiment of the present disclosure. Furthermore, the described features, advantages, and characteristics of the disclosure may be combined in any suitable manner in one or more embodiments. One skilled in the relevant art will recognize that the disclosure may be practiced without one or more of the specific features or advantages of a particular embodiment. In other instances, additional features and advantages may be recognized in certain embodiments that may not be present in all embodiments of the disclosure.

Generally, all terms used herein are to be interpreted according to their ordinary meaning in the relevant technical field, unless a different meaning is clearly given and/or is implied from the context in which it is used. All references to a/an/the element, apparatus, component, means, step, etc. are to be interpreted openly as referring to at least one instance of the element, apparatus, component, means, step, etc., unless explicitly stated otherwise. The steps of any methods disclosed herein do not have to be performed in the exact order disclosed, unless a step is explicitly described as following or preceding another step and/or where it is implicit that a step must follow or precede another step. Any feature of any of the embodiments disclosed herein may be applied to any other embodiment, wherever appropriate. Likewise, any advantage of any of the embodiments may apply to any other embodiments, and vice versa. Other objectives, features and advantages of the enclosed embodiments will be apparent from the following description.

As used herein, the term “network” or “communication network” refers to a network following any suitable wireless communication standards. For example, the wireless communication standards may comprise new radio (NR) , long term evolution (LTE) , LTE-Advanced, wideband code division multiple access (WCDMA) , high-speed packet access (HSPA) , Code Division Multiple Access (CDMA) , Time Division Multiple Address (TDMA) , Frequency Division Multiple Access (FDMA) , Orthogonal Frequency-Division Multiple Access (OFDMA) , Single carrier frequency division multiple access (SC-FDMA) and other wireless networks. In the following description, the terms “network” and “system” can be used interchangeably. Furthermore, the communications between two devices in the network may be performed according to any suitable communication protocols, including, but not limited to, the wireless communication protocols as defined by a standard organization such as 3rd generation partnership project (3GPP) or the wired communication protocols.

The term “network node” used herein refers to a network device or network entity or network function or any other devices (physical or virtual) in a communication network. For example, the network node in the network may include a base station (BS) , an access point (AP) , a multi-cell/multicast coordination entity (MCE) , a server node/function (such as a service capability server/application server, SCS/AS, group communication service application server, GCS AS, application function, AF) , an exposure node/function (such as a service capability exposure function, SCEF, network exposure function, NEF) , a unified data management, UDM, a home subscriber server, HSS, a session management function, SMF, an access and mobility management function, AMF, a mobility management entity, MME, a controller or any other suitable device in a wireless communication network. The BS may be, for example, a node B (NodeB or NB) , an evolved NodeB (eNodeB or eNB) , a next generation NodeB (gNodeB or gNB) , a remote radio unit (RRU) , a radio header (RH) , a remote radio head (RRH) , a relay, a low power node such as a femto, a pico, and so forth.

Yet further examples of the network node may comprise multi-standard radio (MSR) radio equipment such as MSR BSs, network controllers such as radio network controllers (RNCs) or base station controllers (BSCs) , base transceiver stations (BTSs) , transmission points, transmission nodes, positioning nodes and/or the like.

Further, the term “network node” may also refer to any suitable function which can be implemented in a network entity (physical or virtual) of a communication network. For example, the 5G system (5GS) may comprise a plurality of NFs such as AMF (Access and mobility Function) , SMF (Session Management Function) , AUSF (Authentication Service Function) , UDM (Unified Data Management) , PCF (Policy Control Function) , AF (Application Function) , NEF (Network Exposure Function) , UPF (User plane Function) and NRF (Network Repository Function) , RAN (radio access network) , SCP (service communication proxy) , etc. In other embodiments, the network function may comprise different types of NFs (such as PCRF (Policy and Charging Rules Function) , etc. ) for example depending on the specific network.

The term “terminal device” refers to any end device that can access a communication network and receive services therefrom. By way of example and not limitation, the terminal device refers to a mobile terminal, user equipment (UE) , or other suitable devices. The UE may be, for example, a Subscriber Station (SS) , a Portable Subscriber Station, a Mobile Station (MS) , or an Access Terminal (AT) . The terminal device may include, but not limited to, a portable computer, an image capture terminal device such as a digital camera, a gaming terminal device, a music storage and a playback appliance, a mobile phone, a cellular phone, a smart phone, a voice over IP (VoIP) phone, a wireless local loop phone, a tablet, a wearable device, a personal digital assistant (PDA) , a portable computer, a desktop computer, a wearable terminal device, a vehicle-mounted wireless terminal device, a wireless endpoint, a mobile station, a laptop-embedded equipment (LEE) , a laptop-mounted equipment (LME) , a USB dongle, a smart device, a wireless customer-premises equipment (CPE) and the like. In the following description, the terms “terminal device” , “terminal” , “user equipment” and “UE” may be used interchangeably. As one example, a terminal device may represent a UE configured for communication in accordance with one or more communication standards promulgated by the 3GPP, such as 3GPP’ LTE standard or NR standard. As used herein, a “user equipment” or “UE” may not necessarily have a “user” in the sense of a human user who owns and/or operates the relevant device. In some embodiments, a terminal device may be configured to transmit and/or receive information without direct human interaction. For instance, a terminal device may be designed to transmit information to a network on a predetermined schedule, when triggered by an internal or external event, or in response to requests from the communication network. Instead, a UE may represent a device that is intended for sale to, or operation by, a human user but that may not initially be associated with a specific human user.

As yet another example, in an Internet of Things (IoT) scenario, a terminal device may represent a machine or other device that performs monitoring and/or measurements, and transmits the results of such monitoring and/or measurements to another terminal device and/or network equipment. The terminal device may in this case be a machine-to-machine (M2M) device, which may in a 3GPP context be referred to as a machine-type communication (MTC) device. As one particular example, the terminal device may be a UE implementing the 3GPP narrow band internet of things (NB-IoT) standard. Particular examples of such machines or devices are sensors, metering devices such as power meters, industrial machinery, or home or personal appliances, for example refrigerators, televisions, personal wearables such as watches etc. In other scenarios, a terminal device may represent a vehicle or other equipment that is capable of monitoring and/or reporting on its operational status or other functions associated with its operation.

References in the specification to “one embodiment, ” “an embodiment, ” “an example embodiment, ” and the like indicate that the embodiment described may include a particular feature, structure, or characteristic, but it is not necessary that every embodiment includes the particular feature, structure, or characteristic. Moreover, such phrases are not necessarily referring to the same embodiment. Further, when a particular feature, structure, or characteristic is described in connection with an embodiment, it is submitted that it is within the knowledge of one skilled in the art to affect such feature, structure, or characteristic in connection with other embodiments whether or not explicitly described.

It shall be understood that although the terms “first” and “second” etc. may be used herein to describe various elements, these elements should not be limited by these terms. These terms are only used to distinguish one element from another. For example, a first element could be termed a second element, and similarly, a second element could be termed a first element, without departing from the scope of example embodiments. As used herein, the term “and/or” includes any and all combinations of one or more of the associated listed terms.

As used herein, the phrase “at least one of A and (or) B” should be understood to mean “only A, only B, or both A and B. ” The phrase “A and/or B” should be understood to mean “only A, only B, or both A and B. ”

The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example embodiments. As used herein, the singular forms “a” , “an” and “the” are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms “comprises” , “comprising” , “has” , “having” , “includes” and/or “including” , when used herein, specify the presence of stated features, elements, and/or components etc., but do not preclude the presence or addition of one or more other features, elements, components and/or combinations thereof.

It is noted that these terms as used in this document are used only for ease of description and differentiation among nodes, devices or networks etc. With the development of the technology, other terms with the similar/same meanings may also be used.

In the following description and claims, unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skills in the art to which this disclosure belongs.

The NR (new radio) IAB feature is one advanced network-relaying solution that enables multi-hop wireless backhaul with a flexible and adaptive network architecture. 3GPP (3 ^rd generation partnership project) has completed the NR IAB Rel-16 specification work, and is currently standardizing the Rel-17 IAB enhancements. During the study item phase of the IAB work (a technical report, TR 38.874 V16.0.0) , it was agreed to adopt a solution that leverages the Central Unit (CU) /Distributed Unit (DU) split architecture of NR, where the IAB node will be hosting a DU part that is controlled by a central unit. The IAB nodes also have a Mobile Termination (MT) part that they use to communicate with their parent nodes. The specifications for IAB strive to reuse existing functions and interfaces defined in NR. In particular, MT, gNB-DU, gNB-CU, UPF (user plane function) , AMF (access and mobility management function) and SMF (session management function) as well as the corresponding interfaces NR Uu (between MT and gNB) , F1, NG, X2 and N4 are used as baseline for the IAB architectures. Additional functionality such as multi-hop forwarding is included in the architecture discussion as it is necessary for the understanding of IAB operation and new sublayer (Backhaul Adaptation Protocol (BAP) ) is standardized for routing and bearer mapping in IAB network.

FIG. 1 is a reference diagram for an IAB-architectures.

FIG. 1 shows a reference diagram as shown in TR 38.874 V16.0.0 for IAB in standalone mode, which contains one IAB-donor and multiple IAB-nodes. The IAB-donor is treated as a single logical node that comprises a set of functions such as gNB-DU, gNB-CU-CP, gNB-CU-UP and potentially other functions. In a deployment, the IAB-donor can be split according to these functions, which can all be either collocated or non-collocated as allowed by 3GPP NG-RAN architecture.

As mentioned above, a new protocol layer called Backhaul Adaptation Protocol (BAP) has been introduced in the IAB (Integrated Access Backhaul) nodes and the IAB donor, which is located above the RLC layer as shown in FIG. 2. The BAP layer is used for routing of packets to the appropriate downstream/upstream node along with mapping the UE bearer data to the proper backhaul RLC channel (and also between ingress and egress backhaul RLC channels in intermediate IAB nodes) to satisfy the end-to-end QoS requirements of bearers. In other words, the BAP layer is in charge of handling the BH RLC (backhaul radio link control) channel, e.g., to map an ingress BH RLC channel from a parent/child IAB node to an egress BH RLC channel in the link towards a child/parent IAB node. In particular, one BH RLC channel may conveys end-user traffic for several DRBs (Data Radio Bearer) and for different UEs which could be connected to different IAB nodes in the network. In 3GPP two possible configuration of BH RLC channel has been provided, i.e., a 1: 1 mapping between BH RLC channel and a specific user’s DRB, a N: 1 bearer mapping where N DRBs possibly associated to different UEs are mapped to 1 BH RLC channel.

Such IAB-architectures are particularly useful in many cases and scenarios. For example, movable base station may be quickly deployed by utilizing IAB-architectures, when a geographical area of interest cannot be fully covered by the existing mobile network.

For example, cases and scenarios may be considered wherein a deployable network node (s) carried on a UAV (s) is/are setup to establish a temporary network to provide temporary coverage/connectivity for a group of interested/authorized users within a geographical area of interest. This geographical area of interest cannot be fully covered by the existing mobile network.

FIG. 3 shows an example of adding two UAV-BSs for providing connectivity to mission critical users in an area with no network coverage or very limited network coverage from the existing mobile network. The two UAV-BSs form a multi-hop relaying scenario, with UAV-BS1 acting as the parent node for UAV-BS2. Different coverage with different height, h (such as h1, h2, h3, etc. ) and different radium, R (such as R1, R2, R3) may be illustrated.

In the disaster area where there is no macro coverage or the original serving macro-BS breaks down, a UAV-BS can be set up to provide mission critical communications to first responders (shown as mission critical (MC) UEs in the figure) . When deploying one UAV BS can’t provide sufficient coverage/capacity to all the MC UEs, more UAV-BSs can be added to boost the coverage/capacity further, which forms a multi-hop relaying scenario as shown in FIG. 3.

Other example use case of using UAV-BSs for providing temporary/on-demand connectivity can be construction, where a standalone temporary network is setup for providing communications for the workers in a construction site with limited public network coverage. Another example use case of such scenario is healthcare in a rural area, where a standalone temporary network is setup to provide local communications to improve the operations for medical personnel in that area.

In a UAV-BS assisted wireless communication network consisting of a set of existing on-ground BS (s) and a set of temporarily added UAV-BS (s) , the deployment and configuration of these UAV-BS (s) play a critical role in the performance of the target users/services (e.g., mission critical users/services) . It can also impact the overall system performance.

As the UAV-BS is connected to the core network using wireless backhaul, it is important to ensure good quality of both the backhaul and access links when performing this system optimization. In addition, the limitations on UAV’s flying altitude, operation time, antenna capabilities and transmit power also put additional constraints on the optimization problem. Furthermore, the optimal solution depends on many factors like network traffic load distribution, QoS requirements, UE movements, transmit power and antenna settings at the nearby on-ground BSs of the UAV-BS, etc.

Therefore, jointly optimizing the 3D-location and the access and backhaul antenna configuration of each UAV-BS in relaying-assisted networks is a complex system-level optimization problem that needs to be solved in a dynamic changing environment.

A good UAV-BS deployment and configuration strategy requires rich data collected at the decision-making entities. Thus, artificial intelligence/machine learning manners may be considered.

3GPP has initiated the discussion on the principles and framework structure for RAN intelligence.

FIG. 4 is a diagram showing a functional framework for RAN Intelligence.

As shown in FIG. 4, in NR Rel-17, 3GPP has conducted studies on enhancement for data collection for NR, where the functional framework for enabling RAN intelligence has been studied based on the current architecture and interfaces. The proposed functional framework, including the AI (artificial intelligence) functionality and the input/output of the component for AI enabled RAN, is shown in FIG. 4.

Data Collection is a function that provides input data to Model training and Model inference functions. AI/ML algorithm specific pre-processing of data is not carried out in the Data Collection function.

Examples of input data may include measurements from UEs or different network entities, performance feedback, AI/ML model output.

Training Data refers to information needed for the AI/ML model training function.

Inference Data refers to information needed as an input for the Model inference function to provide a corresponding output.

Model Training is a function that performs the training of the ML model. The Model training function is also responsible for data preparation (e.g., data pre-processing and cleaning, formatting, and transformation of raw data) , if required.

Model Inference is a function that provides AI/ML model inference output (e.g., predictions or decisions) . The Model inference function is also responsible for data preparation (e.g., data pre-processing and cleaning, formatting, and transformation of raw data) , if required.

Actor is a function that receives the output from the Model inference function and triggers or performs corresponding actions. The Actor may trigger actions directed to other entities or to itself.

Feedback refers to information that may be needed to derive training or inference data or performance feedback.

However, there is lack of signaling procedure and framework for supporting data collection and decision making for this deployable UAV-BS type of scenarios.

Embodiments for the present disclosure may be provided to solve such problems. Particularly, new signaling procedures and frameworks are proposed to support data collection and decision making for optimizing the deployment and configuration of a movable base station (such as UAV-BS) , which is temporarily integrated into a wireless communication network using wireless backhaul.

Both centralized and distributed frameworks may be proposed for the data collection and decision making, considering the integrated access and backhaul network architecture. In the centralized frameworks, a decision-making entity can be placed either at a IAB drone node or an edge-cloud, or a UAV-BS. In the distributed frameworks, a decision-making entity may be placed at each of the UAV-BSs.

For each proposed framework, key signaling procedures are proposed, including the control signaling for triggering/updating/stopping data collection, data reporting and feedback between different functionalities for system optimization, and signaling for forwarding decision (s) to the related entities (e.g., UAV-BSs and on-ground BSs) .

Taking machine learning as an example of algorithms for UAV-BS deployment and configuration-optimization, it is illustrated how the proposed new signaling procedures and frameworks can be used to support different use cases and deployment options (e.g., system-optimization functionalities hosted by different nodes, UAV-BS/Donor-BS to trigger data collection/reporting, single-hop/multi-hop relaying, etc. ) .

As shown in FIG. 5, the method may comprise: S102, collecting, by a data collection module, data about measurements and/or performance metrics relating to at least one terminal device to be served by at least one movable base station; S104, determining, by a model inference module, configuration for deploying the at least one movable base station, based on at least part of the collected data; and S106, actuating, by an actor module, the at least one movable base station, based on at least the determined configuration.

The method may be implemented in a computer or any other kinds of computing devices, apparatuses, etc. The method may be for developing at least one movable base station to serve at least one terminal device in the communication network. The at least one terminal device is served either by a network node or served through the at least one movable base station which has a wireless backhaul link communicating with the network node functioning as a donor base station.

The determined configuration optimizes at least one of the performances metrics at the at least one terminal device, and by using the determined configuration, the at least one of the performances metrics is better when the at least one terminal device is served by the movable base station comparing to when the at least one terminal device is served by the network node.

According to embodiments of the present disclosure, the proposed procedure can enable data collection from different network entities. It also enables using the collected data for optimization algorithms to solve the complicated system optimization problem, and thereby making a proper decision on the deployment and configuration of the movable base station.

The above data, such as the previously applied configuration and relating previous performance metrics, may be collected continually and repeatedly during the developing. Thus, the new configuration to be applied may be improved continually and iteratively.

In embodiments of the present disclosure, the method further comprises: S103, training and updating a model used by the model inference module, by the model training module, based on at least the training data and/or feedback from the model inference module.

In embodiments of the present disclosure, the model inference module determines the configuration, by inputting a part of the collected data to the model and obtaining an output from the model; and/or the model inference module outputs the configuration to the model training module as feedback.

In embodiments of the present disclosure, a target movable base station in the at least one movable base station is connected to the donor base station via multi-hop wireless backhauling. The multi-hop wireless backhauling comprises at least one intermediate movable base station. The target movable base station is operative for: collecting the data, via data reports from the at least one terminal device, and/or at least one intermediate movable base station, and/or the donor base station, and/or a set of other selected base stations; training a model used by the model inference module, based on at least part of the collected data; cooperating with the at least one intermediate movable base station for generating the configuration for deploying the target movable base station, based on at least part of the collected data and feedback from the at least one intermediate movable base station; taking action, based on the configuration; and feedbacking the configuration to the at least one intermediate movable base station, and/or the donor base station, and/or a set of other selected base stations. The at least one intermediate movable base station is operative for: cooperating with the target movable base station for generating another configuration for deploying the at least one intermediate movable base station, and/or other intermediate movable base stations, based on at least part of the collected data and feedback from the target movable base station; feedbacking another configuration to the donor base station, and/or the set of other selected base stations.

According to embodiments, specific signaling procedures in different scenarios are also provided, and thereby enables a proper decision on the deployment and configuration of the movable base station in these different scenarios.

Particularly, the proposed procedure and frameworks can enable data collection from different network entities (e.g., BS, IAB nodes, cloud) , UAV-BSs and UEs. They also enable using the collected data for ML or other optimization algorithms to solve the complicated system optimization problem, and thereby making a proper decision on the deployment and configuration of the UAV-BSs.

FIG. 6 shows an example of adding two UAV-BSs for providing connectivity to mission critical users in an area with no network coverage or very limited network coverage from the existing mobile network. The two UAV-BSs are connected to different on-ground donor BSs.

UAV-BS assisted wireless network scenarios as in the examples shown in FIG. 3 and FIG. 5 may be considered. Depending on the traffic needs, a single or multiple UAV-BSs is/are added into an existing mobile network to provide additional coverage/capacity. A UAV-BS connects to a parent node or a donor node using wireless backhaul, and it serves on-ground users using access links. The network topology (e.g., number of wireless backhaul hops, the parent and child node association) is adapted based on the traffic needs and channel conditions. FIG. 3 and FIG. 6 show two different network topology examples when adding two UAV-BSs into an existing mobile network. One technology of enabling this flexible network topology adaptation is IAB, as introduced with reference to FIG. 1 and FIG. 2.

A UAV-BS can adjust its parameters like its 3D (3 dimensions) position, antenna tilting, beamforming, and/or rotation/orientation, to best serve the on-ground users and at the same time maintain good wireless backhaul connections.

In following, the signaling and procedures for data collection and decision making for optimizing the deployment and configuration of a UAV-BS will be further described, considering different optimization functional architectures (optimization models hosed by different nodes) and different deployment scenarios (UAV-BS/Donor-BS to trigger data report, single-hop/multi-hop) .

AI/ML is selected as one example of optimization methods, and the introduced NR AI/ML framework is used to show how the proposed signaling procedures can be applied in this framework. It should be noted that the proposed methods can be applied to other optimization algorithms as well. For example, empirical functions, expert systems may be also used.

In following, several signaling examples are proposed focusing on different scenarios respectively. The key difference between these examples is shown in Table I and highlighted as underlined in the description of each example.

Examples 1-10 and examples 11-12 can be applied to reinforcement learning and federated learning respectively. Specifically, the federated learning procedure in examples 11 and 12 can also be applied in the model training and model update steps of examples who are marked as “Distributed” in the “AI/ML Type” column of Table I.

The procedures proposed in examples 1-8 assume a single-time data collection when triggered. In examples 9-10, it is shown how the procedures in examples 1-2 can be extended to support periodic/multiple-time data collection when needed. The same methodology used in examples 9-10 can be applied for examples 1-8 to support periodic/multiple-time data collection as well.

Table I. Key distinction between different examples

FIG. 7 is a diagram showing a signaling procedure for example 1.

FIG. 7 shows a signaling procedure for the “Single-Hop Backhaul Link &Donor-BS Trigger &UAV-BS Hosting AI Model” scenario.

A single UAV-BS or multiple UAV-BSs connected to a donor-BS wirelessly. The target UAV-BS is connected to a donor-BS via single-hop wireless backhauling. Each of the UAV-BS (s) provides wireless access links to MC UEs within its coverage.

Data collection for optimizing a UAV-BS configuration and deployment is triggered by a donor-BS.

Optimization related functions including data collection, model training, model inference and actor are all hosted in each of the UAV-BSs. The advantage is to reduce excessive signaling between the UAV-BSs and the network and simplify the implementation, by making local decisions at each UAV-BS.

A UAV-BS collects data from its connected MC users, the donor-BS, and other related BSs (e.g., IAB nodes, other UAV-BSs and/or macro-BSs) .

The set of related BSs can be selected based on the backhaul or/and access link quality measurements, inter-cell interference measurements, location information of the BSs, and/or location information of interested users (e.g., MC UEs) .

Depending on the feedback from a UAV-BS, the donor-BS and other related BSs may apply certain actions to assist the system optimization.

The proposed procedure consists at least a subset of the following steps (11) - (17) .

(11) Data request triggered by a donor-BS: After a UAV-BS completing its network integration procedure, or when a UAV-BS mobility event has been detected (e.g., a UAV-BS has adjusted its location) , the donor-BS triggers data collection to assist the UAV-BS to optimize its configuration and deployment.

This UAV-BS may be referred as the target UAV-BS. There can be multiple target UAV-BSs depending on the deployment scenarios. In this case, the proposed procedure may be applied to each of the target UAV-BSs.

(12) Data collection at the target UAV-BS: After receiving data request message, MC users, donor-BSs, related on-ground BSs (e.g., IAB nodes and/or macro-BSs) , and other related UAV-BSs will send the requested data to the target UAV-BS.

The shared data can be raw data based on the measurements, KPIs (Key Performance Indicator) , or post-processed data. A detailed list of data can be found in below description.

The data collection procedure can provide following data:

Data collected by the target UAV-BS itself, e.g., from its connected MC users, its own radio measurements, on-board sensors, cameras, etc.

Data firstly reported from a set of users, a set of on-ground BSs (e.g., on-ground IAB nodes or macro-BSs) , and/or a set of other UAV-BSs to the donor-BS, and then forwarded from the donor-BS to the target UAV-BS. The forwarded data can be the raw data or post-processed data.

(13) Learning process in the target UAV-BS: With data collecting from external sources and self-collected data, the AI model begins to perform data pre-processing, cleaning, formatting and transformation. Then, the model training and inference processes are initiated using the processed data. After training, a set of ML-related parameters are generated corresponding to trained model. Then, the learning-based deployment strategy and suggested configuration are generated based on the output of model inference.

(14) The target UAV-BS takes action. The actor in the target UAV-BS performs (re) configuration or/and movement based on the output of the model inference.

(15) The target UAV-BS sends feedback to its donor-BS, who can also forward the feedback to related on-ground BSs or other UAV-BSs. The feedback includes recommendations on the configuration/adjustment of the related BSs.

(16) The donor-BS and/or the related BSs adjust their configuration. The feedback from the target UAV-BS can be used as an input data for the donor-BS and/or related BSs to make a decision next time on whether or not to adjust its configuration (e.g., antennal tilting and transmit power, location, etc) to improve the system performance. For other UAV-BSs, they can also consider the feedback as an input data for the next time when they perform a training/inference step.

(17) Donor-BS stops requesting data report, by e.g., sending messages to its connected MC users, UAV-BSs and/or other related BSs.

FIG. 8 is a diagram showing a signaling procedure for example 2.

FIG. 8 shows a signaling procedure for “Single-Hop Backhaul Link &UAV-BS Trigger &UAV-BS Hosting AI Model” scenario.

Data collection for optimizing a UAV-BS configuration and deployment is triggered by the UAV-BS itself.

The proposed procedure consists at least a subset of the following steps: (21)

(21) Data request triggered by a UAV-BS: After a UAV-BS completing its network integration procedure, or when a UAV-BS initiates a mobility event (e.g., a UAV-BS adjusts its location) , the UAV-BS triggers data collection to optimize its configuration deployment.

This UAV-BS is referred as the target UAV-BS. There can be multiple target UAV-BSs depending on the deployment scenarios. In this case, the proposed procedure is applied to each of the target UAV-BSs.

(22) Data collection at the target UAV-BS is same as the data collection procedure of example 1.

(23) Learning process in the target UAV-BS is same as the learning process procedure of example 1.

(24) The target UAV-BS takes action. The actor in the target UAV-BS performs (re) configuration or/and movement based on the output of the model inference.

(25) The target UAV-BS sends feedback to its donor-BS, who can also forward the feedback to related on-ground BSs or other UAV-BSs. The feedback includes recommendations on the configuration/adjustment of the related BSs.

(26) The donor-BS and/or the related BSs adjust their configuration, as same as the description for corresponding procedure in example 1.

(27) UAV-BS stops requesting data report, by e.g., sending messages to its connected MC users, donor-BS and/or other related BSs.

FIG. 9 is a diagram showing a signaling procedure for example 3.

FIG. 9 shows signaling procedure for “Single-Hop Backhaul Link &Donor-BS Trigger &Donor-BS Hosting AI Model” scenario.

Optimization related functions including data collection, model training, model inference and actor are all hosted in the donor-BS of the target UAV-BS. The advantage is to offload the load on target UAV-BS and improve its power efficiency.

A donor-BS collects data from its connected MC users, its associated UAV-BS, and other related BSs (e.g., IAB nodes, other UAV-BSs and/or macro-BSs) .

Depending on the feedback from a donor-BS, the target UAV-BS and other related BSs may apply certain actions to assist the system optimization.

The proposed procedure consists at least a subset of the following steps:

(31) Data request triggered by a donor-BS is same as the data request trigger procedure of example 1.

(32) Data collection at the donor-BS: After receiving data request message, MC users, UAV-BSs associated with the donor-BS, related on-ground BSs (e.g., IAB nodes and/or macro-BSs) , and other related UAV-BSs will send the requested data to the donor-BS.

The shared data can be raw data based on the measurements, KPIs, or post-processed data. A detailed list of data can be found in below.

The data collection procedure can provide data including:

Data collected by the donor-BS itself, e.g., from its connected MC users, its own radio measurements, on-board sensors, cameras, etc.

Data reported from a set of users, a set of on-ground BSs (e.g., on-ground IAB nodes or macro-BSs) , and/or a set of UAV-BSs to the donor-BS.

The forwarded data can be the raw data or post-processed data.

(33) Learning process in the donor-BS: With data collecting from external sources and self-collected data, the AI model begins to perform data pre-processing, cleaning, formatting and transformation. Then, the model training and inference processes are initiated using the processed data. After training, a set of ML-related parameters are generated corresponding to trained model. Then, the learning-based deployment strategy and suggested configuration is generated based on the output of model inference.

(34) The donor-BS sends feedback to its associated UAV-BS, and other related on-ground BSs or other UAV-BSs. The feedback includes recommendations on the configuration/adjustment of the related BSs.

(35) The target UAV-BS takes action. The target UAV-BS performs (re) configuration or/and movement based on the feedback from the actor in its donor-BS.

(36) The related BSs adjust their configuration. The feedback from the donor-BS can be used as an input data for the target UAV-BS and/or related BSs to make a decision next time on whether or not to adjust its configuration (e.g., antennal tilting and transmit power, location, etc) to improve the system performance.

(37) Donor-BS stops requesting data report, by e.g., sending messages to its connected MC users, UAV-BSs and/or other related BSs.

FIG. 10 is a diagram showing a signaling procedure for example 4.

FIG. 10 shows a signaling procedure for “Single-Hop Backhaul Link &UAV-BS Trigger &Donor-BS Hosting AI Model” scenario.

The proposed procedure consists at least a subset of the following steps:

(41) Data request triggered by a UAV-BS is same as the data request trigger procedure of example 2.

(42) Data collection at the donor-BS is same as the data collection procedure of example 3.

(43) Learning process in the donor-BS is same as the data collection procedure of example 3.

(44) The donor-BS sends feedback to its associated UAV-BS, and other related on-ground BSs or other UAV-BSs. The feedback includes recommendations on the configuration/adjustment of the related BSs.

(45) The target UAV-BS takes action. The target UAV-BS performs (re) configuration or/and movement based on the feedback from the actor in its donor-BS.

(46) The related BSs adjust their configuration, as same as the description for corresponding procedure in example 3.

(47) UAV-BS stops requesting data report, by e.g., sending messages to its connected MC users, donor-BS and/or other related BSs.

FIG. 11 is a diagram showing a signaling procedure for example 5.

FIG. 11 shows a signaling procedure for “Single-Hop Backhaul Link &Donor-BS Trigger &Co-Hosting AI Model” scenario.

Optimization related functions including data collection, model inference and actor are all hosted in each of the UAV-BSs and donor-BS. The model training function is only hosed in donor-BS, which means only donor-BS can train the learning model with collected data. The UAV-BSs receive trained model from its donor-BS and use it for model inference. The advantage is to let UAV-BSs make local decision but not consuming resource on model training.

A UAV-BS and its donor-BS collect and exchange data from respective connected MC users, and other related BSs (e.g., IAB nodes, other UAV-BSs and/or macro-BSs) .

The donor-BS also receives feedback from the target UAV-BS and may apply certain action to assist the system optimization.

The proposed procedure consists at least a subset of the following steps:

(51) Data request triggered by a donor-BS, is same as the data request trigger procedure of example 1.

(52) Data collection at the UAV-BS and its donor-BS: After receiving data request message, MC users, UAV-BSs associated with the donor-BS, related on-ground BSs (e.g., IAB nodes and/or macro-BSs) , and other related UAV-BSs will send the requested data to the donor-BS. Meanwhile, MC users and donor-BS will also send the related data to the target UAV-BS.

The data collection procedure can include following data.

For target UAV-BS, data may be collected by the target UAV-BS itself, e.g., from its connected MC users, its own radio measurements, on-board sensors, cameras, etc. Data may be firstly reported from a set of users, a set of on-ground BSs (e.g., on-ground IAB nodes or macro-BSs) , and/or a set of other UAV-BSs to the donor-BS, and then forwarded from the donor-BS to the target UAV-BS.

For donor-BS, data may be collected by the donor-BS itself, e.g., from its connected MC users, its own radio measurements, on-board sensors, cameras, etc. Data may be reported from a set of users, a set of on-ground BSs (e.g., on-ground IAB nodes or macro-BSs) , and/or a set of UAV-BSs to the donor-BS.

The forwarded data can be the raw data or post-processed data.

(53) Model update in the target UAV-BS: The donor-BS also send its trained model to the target UAV-BS for model update.

(54) Learning process in the donor-BS is same as the data collection procedure of example 3.

(55) Learning process in the target UAV-BS is same as the learning process procedure of example 1.

(56) The donor-BS sends feedback to its associated UAV-BS, and other related on-ground BSs or other UAV-BSs. The feedback includes recommendations on the configuration/adjustment of the related BSs.

(57) The target UAV-BS sends feedback to its donor-BS, who can also forward the feedback to related on-ground BSs or other UAV-BSs. The feedback includes recommendations on the configuration/adjustment of the related BSs.

(58) The target UAV-BS takes action. The target UAV-BS performs (re) configuration or/and movement based on the output of its model inference function and the feedback from its donor-BS.

(59) The donor-BS takes action. The donor-BS performs (re) configuration or/and movement based on the output of its model inference function and the feedback from the target UAV-BS.

(510) The related BSs adjust their configuration. The feedback from the target UAV-BS and/or donor-BS can be used as an input data for related BSs to make a decision next time on whether or not to adjust its configuration (e.g., antennal tilting and transmit power, location, etc) to improve the system performance. For other UAV-BSs, they can also consider the feedback as an input data for the next time when they perform an inference step.

(511) Donor-BS stops requesting data report, by e.g., sending messages to its connected MC users, UAV-BSs and/or other related BSs.

FIG. 12 is a diagram showing a signaling procedure for example 6.

FIG. 12 shows a signaling procedure for “Single-Hop Backhaul Link &UAV-BS Trigger &Co-Hosting AI Model” scenario.

The proposed procedure consists at least a subset of the following steps:

(61) Data request triggered by a UAV-BS is same as the data request trigger procedure of example 2.

(62) Data collection at the UAV-BS and its donor-BS is same as the data collection procedure of example 5.

(63) Model update in the target UAV-BS: The donor-BS also send its trained model to the target UAV-BS for model update.

(64) Learning process in the donor-BS is same as the data collection procedure of example 3.

(65) Learning process in the target UAV-BS is same as the learning process procedure of example 1.

(66) The donor-BS sends feedback to its associated UAV-BS, and other related on-ground BSs or other UAV-BSs. The feedback includes recommendations on the configuration/adjustment of the related BSs.

(67) The target UAV-BS sends feedback to its donor-BS, who can also forward the feedback to related on-ground BSs or other UAV-BSs. The feedback includes recommendations on the configuration/adjustment of the related BSs.

(68) The target UAV-BS takes action. The target UAV-BS performs (re) configuration or/and movement based on the output of its model inference function and the feedback from its donor-BS.

(69) The donor-BS takes action. The donor-BS performs (re) configuration or/and movement based on the output of its model inference function and the feedback from the target UAV-BS.

(610) The related BSs adjust their configuration, as same as the description for corresponding procedure in example 5.

(611) UAV-BS stops requesting data report, by e.g., sending messages to its connected MC users, donor-BS and/or other related BSs.

FIG. 13 is a diagram showing a signaling procedure for example 7.

FIG. 13 shows a signaling procedure for “Multi-Hop Backhaul Link &Donor-BS Trigger &UAV-BS Hosting AI Model” scenario.

A single UAV-BS or multiple UAV-BSs connected to a donor-BS wirelessly. The target UAV-BS is connected to a donor-BS via multi-hop wireless backhauling. Each of the UAV-BS (s) provides wireless access links to MC UEs within its coverage.

A UAV-BS and its parent/child UAV-BSs collect and exchange data from respective connected MC users, the donor-BS, and other related BSs (e.g., IAB nodes, other UAV-BSs and/or macro-BSs) .

The parent/child nodes of a target UAV-BS refer to the UAV-BSs that have direct backhaul link with the target UAV-BS.

The target UAV-BS and its parent/child UAV-BS can also send feedback to each other and may apply certain actions to assist the system optimization.

The proposed procedure consists at least a subset of the following steps:

(71) Data request triggered by a donor-BS, is same as the data request trigger procedure of example 1.

(72) Data collection at the UAV-BS and its parent/child UAV-BSs: After receiving data request message, MC users, UAV-BSs associated with the donor-BS, related on-ground BSs (e.g., IAB nodes and/or macro-BSs) , and other related UAV-BSs will send the requested data to the target UAV-BS and its parent/child UAV-BSs.

The data collection procedure can include: data collected by the target UAV-BS and its parent/child UAV-BSs, e.g., from respective connected MC users, own radio measurements, on-board sensors, cameras, etc; data firstly reported from a set of users, a set of on-ground BSs (e.g., on-ground IAB nodes or macro-BSs) , and then forwarded from the donor-BS to the target UAV-BS and its parent/child UAV-BSs. The forwarded data can be the raw data or post-processed data.

(73) Learning process in the target UAV-BS and its parent/child UAV-BSs, is same as the learning process procedure of example 1.

(74) The target UAV-BS sends feedback to its parent/child UAV-BSs, who can also forward the feedback to the donor-BS, related on-ground BSs or other UAV-BSs. The feedback includes recommendations on the configuration/adjustment of the related BSs.

(75) The parent/child UAV-BSs send feedback to the target UAV-BS, and other related on-ground BSs or other UAV-BSs. The feedback includes recommendations on the configuration/adjustment of the related BSs.

(76) The target UAV-BS takes action. The target UAV-BS performs (re) configuration or/and movement based on the output of its model inference function and the feedback from its parent/child UAV-BSs.

(77) The parent/child UAV-BS takes action. The parent/child UAV-BS performs (re) configuration or/and movement based on the output of its model inference function and the feedback from the target UAV-BS.

(78) The donor-BS and/or the related BSs adjust their configuration. Same as the description for corresponding procedure in example 1.

(79) Donor-BS stops requesting data report, by e.g., sending messages to its connected MC users, UAV-BSs and/or other related BSs.

FIG. 14 is a diagram showing a signaling procedure for example 8.

FIG. 14 shows a signaling procedure for “Multi-Hop Backhaul Link &UAV-BS Trigger &UAV-BS Hosting AI Model” scenario.

The proposed procedure consists at least a subset of the following steps:

(81) Data request triggered by a UAV-BS is same as the data request trigger procedure of example 2.

(82) Data collection at the UAV-BS and its parent/child UAV-BSs is same as the data collection procedure of example 7.

(83) Learning process in the target UAV-BS and its parent/child UAV-BSs is same as the learning process procedure of example 1.

(84) The target UAV-BS sends feedback to its parent/child UAV-BS, who can also forward the feedback to its donor-BS, related on-ground BSs or other UAV-BSs. The feedback includes recommendations on the configuration/adjustment of the related BSs.

(85) The parent/child UAV-BSs send feedback to the target UAV-BS, and other related on-ground BSs or other UAV-BSs. The feedback includes recommendations on the configuration/adjustment of the related BSs.

(86) The target UAV-BS takes action. The target UAV-BS performs (re) configuration or/and movement based on the output of its model inference function and the feedback from its parent/child UAV-BSs.

(87) The parent/child UAV-BS takes action. The parent/child UAV-BS performs (re) configuration or/and movement based on the output of its model inference function and the feedback from the target UAV-BS.

(88) The donor-BS and/or the related BSs adjust their configuration, as same as the description for corresponding procedure in example 1.

(89) UAV-BS stops requesting data report, by e.g., sending messages to its connected MC users, donor-BS, its parent/child UAV-BSs and/or other related BSs.

FIG. 15 is a diagram showing a signaling procedure for example 9.

FIG. 15 shows a signaling procedure for “Single-Hop Backhaul Link &Data Update &Donor-BS Trigger &UAV-BS Hosting AI Model” scenario.

After learning process based on collected data , donor-BS might trigger data update procedure to refine the learning model before or after a UAV-BS taking action. The data update trigger message might include but not limited to information about the periodicity, content and used resource for the transferred data.

The proposed procedure consists at least a subset of the following steps (Normal procedures for data collection and feedback are collapsed as data update procedure is the focus of this sub-section) :

(91) Learning process in the target UAV-BS is same as the learning process procedure of example 1.

(92) Data update triggered by a donor-BS (Optional) : When the model training function requires new data to refine the trained model (e.g., donor-BS observes performance decline) , the donor-BS triggers data update to collect new data.

(93) Re-learning process in the target UAV-BS (Optional) is same as the learning process procedure of example 1. The AI model is refined after this step.

(94) The target UAV-BS takes action. The actor in the target UAV-BS performs (re) configuration or/and movement based on the output of the model inference.

(95) Data update triggered by a donor-BS (Optional) : When the model training function requires new data to refine the trained model (e.g., donor-BS observes performance decline) , the donor-BS triggers data update to collect new data.

(96) Re-learning process in the target UAV-BS (Optional) : Same as the learning process procedure of example 1. The AI model is refined after this step.

(97) The target UAV-BS takes action (Optional) . The actor in the target UAV-BS performs (re) configuration or/and movement based on the output of the refined model inference.

FIG. 16 is a diagram showing a signaling procedure for example 10.

FIG. 16 shows a signaling procedure for “Single-Hop Backhaul Link &Data Update &UAV-BS Trigger &UAV-BS Hosting AI Model” scenario.

Data collection for optimizing a UAV-BS configuration and deployment is triggered by UAV-BS itself.

After learning process based on collected data, a UAV-BS might trigger data update procedure to refine the learning model before or after a UAV-BS taking action. The data update trigger message might include but not limited to information about the periodicity, content and used resource for the transferred data.

(101) Learning process in the target UAV-BS is same as the learning process procedure of example 1.

(102) Data update triggered by a UAV-BS (Optional) : When the model training function requires new data to refine the trained model (e.g., due to the AI model can’t provide decision to guarantee considerable performance) , the target UAV-BS triggers data update to collect new data.

(103) Re-learning process in the target UAV-BS (Optional) : is same as the learning process procedure of example 1. The AI model is refined after this step.

(104) The target UAV-BS takes action: The actor in the target UAV-BS performs (re) configuration or/and movement based on the output of the model inference.

(105) Data update triggered by a UAV-BS (Optional) : When the model training function requires new data to refine the trained model (e.g., due to the AI model can’t provide decision to guarantee considerable performance) , the target UAV-BS triggers data update to collect new data.

(106) Re-learning process in the target UAV-BS (Optional) is same as the learning process procedure of example 1. The AI model is refined after this step.

(107) The target UAV-BS takes action (Optional) . The actor in the target UAV-BS performs (re) configuration or/and movement based on the output of the refined model inference.

FIG. 17 is a diagram showing a signaling procedure for example 11.

FIG. 17 shows a signaling procedure for the “Single-Hop Backhaul Link &Donor-BS Trigger &UAV-BS Hosting AI Model &Donor-BS as Central Server” scenario.

Data collection for optimizing a UAV-BS configuration and deployment is t riggered by a donor-BS, who is also acting as a central server.

A UAV-BS collects local data e.g., from its connected MC users and its neighboring BSs.

Depending on the trained local model feeding back from a UAV-BS, the central server hosted in the donor-BS aggregates the training results (e.g., trained local model) collecting from its associated UAV-BSs and update the global learning model.

The proposed procedure consists at least a subset of the following steps:

(111) Model update triggered by a donor-BS: After a UAV-BS completing its network integration procedure, or when a UAV-BS mobility event has been detected (e.g., a UAV-BS has adjusted its location) , the donor-BS triggers model update by sending centralized learning model to assist the UAV-BS to optimize its configuration and deployment.

This UAV-BS may be referred as the target UAV-BS. There can be multiple target UAV-BSs depending on the deployment scenarios. In this case, the proposed procedure is applied to each of the target UAV-BSs.

(112) Receiving the centralized learning model at the target UAV-BS.

(113) Local data collection at the target UAV-BS: After receiving data request message, related MC users and BSs will send the requested data to the target UAV-BS.

The data collection procedure can include: data collected by the target UAV-BS itself, e.g., from its connected MC users, its neighboring BSs, its own radio measurements, on-board sensors, cameras, etc.

(114) Learning process in the target UAV-BS: Each UAV BS can gradually learn and train its local model based on its locally collected data.

(115) The target UAV-BS takes action. The actor in the target UAV-BS performs (re) configuration or/and movement based on the output of the model inference.

(116) The target UAV-BS sends feedback to the central server (donor-BS) . The feedback includes training results (e.g., trained local model) from the target UAV-BS.

(117) The donor-BS aggregates the training results (e.g., trained local model) from its related UAV-BSs. Based on the feedback from the target UAV-BS, the donor-BS aggregates the results transferred from all related UAV BSs, and updates its centralized learning model.

(118) Repeat above process if needed.

FIG. 17 is a diagram showing a signaling procedure for example 12.

FIG. 18 shows a Signaling procedure for the “Single-Hop Backhaul Link &UAV-BS Trigger &UAV-BS Hosting AI Model &Donor-BS as Central Server” scenario.

The description is the same as example 11 and the only difference is that the data collection for optimizing a UAV-BS configuration and deployment is triggered by a UAV-BS.

The proposed procedure consists at least a subset of the following steps:

(121) Model update triggered by a UAV-BS: After a UAV-BS completing its network integration procedure, or when a UAV-BS initiates a mobility event (e.g., a UAV-BS adjusts its location) , the UAV-BS triggers data collection and model update request by to optimize its configuration and deployment.

Further following procedure can follow all the steps after “ Model update triggered by a donor-BS” in example 11.

FIG. 19: Structure of proposed optimization-based framework

As shown in FIG. 19, the proposed signaling procedure may be applied into the 3GPP ML-based framework.

Based on the 3GPP framework introduced in the FIG. 4, a detailed optimization-based framework is designed to collect data from different network entities and perform optimization based on collected data, as shown in FIG. 19. The detailed introduction of each module is described as follows.

Data Collection is deployed at network side to collect measurements and performance metrics from MC users and corresponding serving BSs.

It is suggested to put this module near the data source to reduce excessive signalling.

The collected data is divided into two sub-sets as training data and inference data for different modules, respectively.

Examples of the collected data include but not limited to at least one of the following.

General information:

The load situation and resource utilization of the network;

The geographic information of MC area;

Macro information, such as Antenna tilting, transmit power.

UAV configuration:

Electrical/mechanical antenna tilting, rotation, 3D location, transmit power.

Performance metrics in the case of current configuration:

Throughput distribution (5%, 50%and 95%percentile) , SINR and drop rate of all users for both DL and UL.

Backhaul:

Link quality: SINR (Signal to Interference plus Noise Ratio) , RSRP (Reference Signal Receiving Power) , RSRQ (Reference Signal Receiving Quality) , RSSI (Received Signal Strength Indication) ;

Link rate and drop rate.

IAB-specific information: Donor node (parent node, children node, tilting) , number of hops.

User information:

Labels to distinguish different types of users (MC and normal users) ;

Statistics: Proportion of MC users served by UAV;

User mobility information: User speed, historical information.

Meanwhile the data collection module also receives and applies feedback from the learning modules, including deployment strategy or suggested configuration (optimal antenna configuration or UAV location to serve MC users) based on algorithm prediction.

Training Data may refer to information needed for the optimization model training function.

Inference Data may refer to information needed as an input for the Model inference function to provide a corresponding output.

For the data collection part, it is critical to decide when, how and who to trigger data transferring from other nodes to the optimization model. Hence two options are provided as following.

As option 1, after the UAV-BS completing its network integration procedure, its donor node starts to trigger a set of IAB nodes (e.g., other UAV-BSs, truck-BSs, fixed IAB nodes) or/and a set of macro-BSs to transfer the data to UAV-BS for optimization model training and inference.

The set of network nodes (IAB nodes, or macro-BSs) can be selected based on the backhaul link quality measurements and/or interference measurements and/or location information collected at the donor node.

As option 2, a signaling from the UAV-BS is used to trigger related network nodes to transmit the data for optimization model training and inference.

A) The triggering message is broadcasted by the UAV-BS, i.e., via a broadcasting message. The network nodes that can detect this message will start transferring data to the UAV-BS.

B) The triggering message is signalled only to a set of selected network nodes, i.e., via unicasting or multicasting message. These network nodes can be selected based on the link quality measurements and interference information available at the UAV-BS or the information feedback from its collected UEs.

Model Training can be deployed at network side (donor BS, UAV-IAB BS or cloud depending on implementation) to performs the training of the optimization model with the training data collected from data collection module.

After training, it will send well-trained model configuration to the model inference module for verification and application.

Then it will receive the performance feedback from the model inference module to calibrate the trained model.

Learning parameters may be adjusted in different scenarios. Based on the data collected from different scenarios (e.g., different network deployment and system load situation) , the trained model may have different optimization-specific parameters. Hence it is necessary to adjust the learning parameters according to the scenario configuration to make the trained model more accurate and applicable.

Reward function may be composed of one/more interested metrics in the form of mathematical equation and is used by the optimization model to evaluate the system performance.

Candidate input features may include any parameter from the collected data, or related to the collected data.

A general expression for the reward function may be: Reward=∑ _i Weight _i*Metric _i, ∑ _i Weight _i=1.

Following exemplary functions may be listed, wherein w ₁…w ₈ are linear weight factors, n ₁…n ₄ (for DL) are exponential weight factors to control the weight of certain metrics in the reward function, m ₁…m ₄ (for UL) are exponential weight factors to control the weight of certain metrics in the reward function, expressions in brackets are different metrics, “perc” means percentile.

Function 1 focusing on MC users:

Function 2 focusing on MC users:

Function 3 focusing on normal users:

Function 4 focusing on normal users:

Function 1-4 can be combined together to form new reward function based on different requirements.

Dynamic metric weight according to some input parameters:

Higher weight for drop rate in case of high load while lower weight for drop rate in case of low load

Higher weight for 5%performance metric in case of high load while higher weight for 50%performance metric in case of low load.

The model training module is also responsible for data preparation (e.g., data pre-processing and cleaning, formatting, and transformation of raw data) , if required.

Model Inference can be deployed at network side (donor BS or UAV-IAB BS depending on implementation) to provide optimization model inference output, such as the deployment strategy or suggested configuration (optimal antenna configuration or UAV location to serve MC users) based on algorithm prediction.

First it receives training results from the model training module and use the trained optimization model to process inference data.

After learning process, the learning results will be sent back to the model training module to refine the optimization model.

The Model inference module is also responsible for data preparation (e.g., data pre-processing and cleaning, formatting, and transformation of raw data) , if required.

As to feedback, based on the output of model inference module, the deployment strategy and suggested configuration will be sent back to the data collector module for application.

Candidate data for optimization model may be further listed below.

Based on the proposed framework illustrated in the previous sub-section, a list of candidate data which is used for the optimization model is introduced:

Data from MC users to UAV-BS and from MC users to donor-BS include:

Labels to distinguish different types of users (MC and normal users) ;

Statistics such as proportion of MC users served by UAV;

User mobility information, such as User speed, historical information;

Throughput and SINR for DL;

RSRP, RSRQ, etc;

Served traffic.

Data from macro-BSs to donor-BS, from donor-BS to UAV-BSs, collected by donor-BS itself and from macro-BSs to donor-BS include:

The load situation and resource utilization of the network;

Antenna tilting, transmit power;

Backhaul and access link rate;

Throughput distribution (5%, 50%and 95%percentile) , SINR and drop rate of all users for both DL and UL;

IAB-specific information.

Data collected by UAV-BS itself, from UAV-BS to donor-BS, shared between UAV-BSs include:

Electrical/mechanical antenna tilting, rotation, 3D location, transmit power;

Backhaul and access link rate for both DL and UL;

Throughput distribution (5%, 50%and 95%percentile) , SINR and drop rate of all users for UL;

IAB-specific information.

These optimization models can be hosted in cloud. All required data can be sent to the cloud for processing. In this case, it is better for the cloud side to initiate/update/stop the data report.

Further detailed application and evaluation of a proposed embodiment may be illustrated below.

Below proposed embodiment may relate to autonomous navigation and configuration of integrated access backhauling for UAV base station using reinforcement learning.

In practice, fast and reliable connectivity is important to enhancing situational awareness and operational efficiency for public safety mission-critical (MC) users. In emergency or disaster circumstances, where existing cellular network coverage and capacity may not be available to meet MC communication demands, deployable-network-based solutions such as cells-on-wheels/wings can be utilized swiftly to ensure reliable connection for MC users. In below, a scenario is considered where a macro base station (BS) is destroyed due to a natural disaster and an unmanned aerial vehicle carrying BS (UAV-BS) is set up to provide temporary coverage for users located in the disaster area. The UAV-BS is integrated into the mobile network using the 5G integrated access and backhaul (IAB) technology. A framework and signalling procedure for applying machine learning to this use case is proposed below. A deep reinforcement learning algorithm is designed to jointly optimize the access and backhaul antenna tilt as well as the three-dimensional location of the UAV-BS, in order to best serve the on-ground MC users while maintaining a good backhaul connection. The result shows that the proposed algorithm can autonomously navigate and configure the UAV-BS to improve the throughput and reduce the drop rate of MC users.

As an introduction, like food, water and medicine, the ability to communicate has proven to be an extremely important tool for first responders, governments, and survivors in disaster response and relief. To provide connectivity in areas that cannot be fully covered by the existing mobile network, e.g., when the network infrastructure is damaged or not available, unmanned aerial vehicles (UAVs) carrying base stations (BSs) can be set up to provide temporary coverage/connectivity for first responders to assist their real-time mission-critical (MC) operations. UAV-BS assist wireless communication networks have recently gained increased interest in both academic and public safety communities [1] – [5] . Thanks to the great mobility and flexibility of UAVs, it is expected that UAV-BSs can bring fast connectivity for MC communications. However, there are a number of challenges that must be addressed when deploying UAV-BSs in practice. In a UAV-BS assisted wireless network consisting of a set of existing on-ground BSs and a set of temporarily added UAV-BSs, the deployment and configuration of these UAV-BSs plays a critical role in the performance of the target services. When integrating a UAV-BS into an existing mobile network, a fast and reliable backhaul connection between the UAV-BS and on-ground BSs is required to ensure the end-to-end quality of service (QoS) for the interested users. In addition, reliable and scalable backhaul links between different UAV-BSs are needed when multiple UAV-BSs are used to cover a wider area. Therefore, it is important to ensure the good quality of both the access and backhaul links when performing the UAV-BS deployment optimization. The deployment optimization also depends on many other factors such as the limitations on UAV’s flying altitude, operation time, antenna capabilities and transmit power, the network traffic load distribution, and user movements, etc. While many works on UAV-BS deployment focused on the problems of UAV placement, trajectory design, and number of UAV-BSs, etc., only a few previous works have considered the wireless backhaul aspects [6] – [9] . In [6] , the authors investigated how to rapidly deploy the minimum number of UAV-BSs to assist the existing mobile network to evenly serve as many users as possible while guaranteeing a robust wireless connection among the UAV-BSs and fixed on-ground BSs. It is assumed that all UAV-BSs are flying at the same and fixed height, and the robustness of the backbone network among the deployed UAV-BSs is guaranteed by ensuring a bi-connection network topology so that if one UAV-BS fails, there still exists at least one route between any UAV-BS and a fixed on-ground BS. In [7] , a UAV-BS 3-D placement algorithm is proposed to maximize the total number of served users or the sum of user data rates subject to capacity constraints of both access and backhaul links. This work was further extended by the authors in [8] , where a mixed-Integer non-linear programming approach is proposed to jointly optimize a UAV-BS location and the system bandwidth allocation without exceeding the backhaul and access capacities.

With 5G new radio (NR) , there is an opportunity to use the integrated access and backhaul (IAB) feature to wirelessly connect multiple UAV-BSs and integrating them to an existing mobile network seamlessly if available [1] , [9] . The NR IAB feature supports multi-hop wireless backhaul with a flexible and adaptive network architecture [10] .

A macro-BS that has a wired connection to the core network is configured as an IAB donor node, and a UAV-BS is configured as an IAB node. The UAV-BS connects to a parent node or donor node using wireless backhaul and it services on-ground users using access links. The IAB network topology (e.g., number of wireless backhaul hops, the parent node and child node association) can adapt according to the varying wireless backhaul link conditions and traffic load situations.

In [9] , the authors evaluated the mean user throughput and user fairness performance of an UAV-based IAB system in millimeter-wave (mmWave) urban deployments, where the UAV-BS location is optimized to follow the user movement using a particle swarm optimization method. They assumed separate channels for access and backhaul links as well as dedicated antenna arrays for each interface. In this work, a UAV-BS assisted IAB network for providing temporary coverage to MC users in an emergency area is considered. It is assumed that the system is operation in a mid-band, which provides better coverage compared to mmWave bands. In addition, the same frequency band as well as the same antennas are shared between access and backhaul links to reduce the cost and weight of the BS carried on the UAV. It is investigated how machine learning (ML) can be used to support autonomous navigation and configuration of IAB for UAV-BS assisted networks. A functional framework and signalling procedure is proposed to support applying ML in an IAB network architecture. In addition, a reinforcement learning algorithm is designed to jointly optimize the antenna configuration as well as the UAV-BS’s 3-D location to best serve on-ground MC users while maintaining a good backhaul connection. Extensive system-level simulations are performed to gain insights into the impact of different optimizing parameters on the considered system performance, i.e., the throughput and drop rate of MC users. The simulation data has also been utilized for the reinforcement learning algorithm design and validation.

The remainder of this embodiment is structured as follows. A section introduces the use case and system model considered in this embodiment. In a section, a framework and signalling procedure to enable ML in an IAB network architecture is proposed. A section discusses the proposed ML algorithm. A section presents the system level simulation results and evaluates the proposed ML algorithm. In a section, the findings are summarized and the future work is discussed.

Below is the section for use case and system model.

A multi-cell mobile cellular network as illustrated in the plot of FIG. 20 (b) is considered. The network originally consists of seven macro-BSs. However, due to e.g., a natural disaster, the macro-BS located in the middle of the network map got damaged. Hence, a UAV-BS is temporally set up to provide wireless connectivity to the MC users located in the disaster area (a circle area with a 350m radius in the middle of the deployment map) . The UAV-BS is modelled as an IAB node. To reduce the complexity and weight of antennas put on the UAV-BS, here it is assumed that the same antennas are used for both the wireless access and backhaul links. The UAV-BS measures the wireless links to the six functioning macro-BSs and it dynamically selects one of these macro-BSs that gives the best link quality as its donor node. Then, a wireless backhaul link is established between the UAV-BS and the selected Macro-BS (i.e., the donor node) . Both normal users and MC users are allowed to access the UAV-BS. A user selects its serving BS (a macro-BS or a UAV-BS) based on the end-to-end wireless path quality.

It is assumed that all macro-BSs and the UAV-BS have three sectors each, and they are operating at the same carrier frequency of 3.5 GHz with a time division duplex (TDD) pattern that consists of four time slots, i.e., downlink (DL) , DL, uplink (UL) and DL. The pattern is repeated with a periodicity of 2ms. The 100 MHz total system bandwidth is shared between the access and backhaul links. To reduce the complexity and mitigate interference, it is further assumed that the UAV-BS is operating in a half-duplex mode, i.e., it cannot transmit and receive signals at the same time. The UAV-BS’s flying height is assumed to be below 35 meters so that the rural macro propagation model can be reused for UAV-BS in this case.

Users are randomly dropped in the deployment map shown in FIG. 20. In each time slot, a number of users are activated following a dynamic traffic model with a predefined traffic arriving rate and a predefined average traffic size. The DL and UL traffic of activated users are scheduled based on the access and backhaul link quality, the network scheduling strategy, and the allowed transmission directions at a given time slot at each BS. The throughput of each served user is calculated based on its served traffic size and the time used for delivering the traffic. Note that for a user connected to the UAV-BS, its throughput depends not only on the access link between itself and the UAV-BS but also on the wireless backhaul link between the UAV-BS and the donor macro-BS. A user will not be served with more traffic than required, and a user can also be dropped/blocked in case of poor link quality or insufficient radio resources. User throughput and drop rate are the key performance indicators considered in the ML algorithm design.

Below is the section for framework and signaling procedure.

In this section, a signalling procedure to support applying ML to the considered use case is proposed. The functional frame-work studied in 5G NR for radio access network intelligence is used as the reference [11] .

The blocks above each entity (UE or BS) shown in FIG. 21 denote different ML functionalities, including data collection, model training, model inference and actor. Data collection is a function that is responsible for collecting and providing input data (e.g., measurements from MC users or other network entities) to model training and model inference functions. The model training function performs the training of the ML model and the model inference function provides learning output (e.g., the antenna configuration and the 3-D location of UAV-BS in the considered case) . Finally, the actor function receives the output from the model inference module and triggers or performs corresponding actions. The proposed signalling procedure is illustrated in FIG. 21, and it consists of the following key steps:

1) : Data requests triggered by a donor BS: After a UAV-BS completing its network integration procedure or when detecting a UAV-BS mobility event, the donor-BS triggers data collection to assist the UAV-BS to optimize its configuration and deployment by sending a data request message to the relevant users and BSs.

2) : Data collection at UAV-BS: After receiving the data re-quest message, MC users, donor-BSs, related on-ground BSs will send the requested data to the UAV-BS. The data collection procedure can include: a) data collected by the UAV-BS itself, e.g., from its connected MC users, radio measurements, on-board sensors, etc. b) data firstly reported from a set of users and a set of on-ground BSs to the donor-BS, and then forwarded to the UAV-BS.

3) : Learning process in the UAV-BS: With the data collecting from external sources and self-collected data, the AI models hosted in the UAV-BS begins to perform data pro-cessing. Then, the model training and inference functions are initiated using the processed data. After training, a set of ML-related parameters are generated corresponding to the trained model. Then, the learning-based deployment strategy and suggested configuration are generated based on the output of model inference.

4) : The UAV-BS takes action. The actor function in the UAV-BS performs antenna tilt and location adjustment based on the output of the model inference.

5) : The UAV-BS sends feedback to its donor-BS, who can then forward the feedback or action recommendations to related on-ground BSs.

6) : The donor-BS and/or the related BSs adjust their con-figuration (e.g., antenna tilt, transmit power, etc. ) , using the feedback from the UAV-BS as input data. Finally, the donor-BS stops requesting data.

Steps 2-6 can repeat till certain criteria are fulfilled. The donor-BS then can stop the ML process by sending a stop data reporting message to its connected users and BSs.

It should be understood that, other procedures in above examples 1-12 may be applied additionally or alternatively.

Below is the section for ml-based algorithm design.

In this section, a reinforcement learning algorithm to jointly optimize the access and backhaul antenna tilt value as well as the 3-D location of the UAV-BS in the considered scenario is designed. Deep Q-Network may be used as base algorithm [12] . The algorithm is modified and implemented to solve system optimization problem.

____________________________________________________________________________

Algorithm 1: Deep Reinforcement Learning for autonomously UAV-BS Control

Algorithm Environment may be also illustrated.

1) As to State Space, a UAV-BS statute at a given time instance t has four dimensions and it is denoted as st = {σt, xt, yt, zt} , where σt represents the electrical tilt value of the access and backhaul antenna, and {xt, yt, zt} denotes the 3-D location of the UAV-BS at time t. The set of candidate values for the x and y axis is [-350, -175, 0, +175, +350] meters, which covers the disaster area shown in FIG. 20. The candidate values of z axis are [10, 20, 30, 35] meters. The candidate antenna tilt values are [-30, -20, -10, 0, +10, +20, +30] °, where a positive tilt value means applying an electrical down-tilt to the access and backhaul antenna, and a negative tilt value maps to applying an electrical up-title to the antenna.

2) As to action Space, for each state dimension, the UAV-BS can select an action out of three candidate options. These three alternative action options are coded by three digits {0, 1, 2} , where “0” denotes that the UAV-BS reduces the status value by one step from its current value; “1” represents that the UAV-BS does not need to take any action at this state dimension and it keeps the current value; and “2” means that the UAV-BS increases the status value by one step from its current value. For instance, if the UAV-BS is at the space point where the value of the x dimension is equal to 0 meter, then, an action coded by “0” for this dimension means that the UAV-BS will select an action to reduce the value of x axis to -175 meters, an action coded by “1” implies that the UAV-BS will hold the current value of x axis (0 meter) , and an action coded by “2” implies that the UAV-BS will increase the value of x axis to 175 meters. The same policy is used for all the dimensions of the state space. Since one state has four dimensions and each state dimension has three action options, the action pool contains in total 81 action candidates that can be programmed to a list of [0000, 0001, 0002, 0010..., 2222] . Hence, at a given time t, the UAV-BS can select an action a _t from these 81 candidates..

For each state dimension, the UAV-BS can select an action out of three candidate options. These three alternative action options are coded by three digits {0, 1, 2} , where “0” denotes that the UAV-BS reduces the status value by one step from its current value; “1” represents that the UAV-BS does not need to take any action at this state dimension and it keeps the current value; and “2” means that the UAV-BS increases the status value by one step from its current value. For instance, if the UAV-BS is at the space point where the value of the x dimension is equal to 0 meter, then, an action coded by “0” for this dimension means that the UAV-BS will select an action to reduce the value of x axis to -175 meters, an action coded by “1” implies that the UAV-BS will hold the current value of x axis (0 meter) , and an action coded by “2” implies that the UAV-BS will increase the value of x axis to 175 meters. The same policy is used for all the dimensions of the state space. Since one state has four dimensions and each state dimension has three action options, the action pool contains in total 81 action candidates that can be programmed to a list of [0000, 0001, 0002, 0010..., 2222] . Hence, at a given time t, the UAV-BS can select an action a _t from these 81 candidates.

3) As to Monitoring Feature Metrics and Reward Function, for MC communications, it is more important to serve as many MC users as possible with adequate service quality rather than maximizing the peak rate of a subset of MC users. Hence, for the reward function design of the reinforcement learning algorithm, six key feature metrics have been chosen to reflect the overall quality of service for MC users, including:

The drop rates of MC users for UL and DL (β _ul, β _dl) , which reflects the percentage of un-served MC users;

The 50-percentile throughput values of MC users for both UL and DL (α _ul-50%α _dl-50%) , which represents the average performance of the MC users; and

The 5-percentile throughput values of MC users for both UL and DL (α _ul-5%, α _dl-5%) , which represents the “worst” performance of the MC users.

To balance these key performance indicators, the reward function is designed as a weighted sum of these six feature values as follows. All features are normalised within the range [0, 1]before model training.

In addition, it is set that ω ₁ + ω ₂ + ω ₃ = 1 to normalise the reward value such that R _s is between [0, 1] . To further emphasise the importance of serving all MC users, larger weight values are put on the user drop rates and 5-percentile MC-user throughput features. The weight values used in the algorithm are ω ₁ = 0.5, ω ₂ = 0.3 and ω ₃ = 0.2.

In order to achieve better self-control decisions for the autonomous UAV-BS, deep Q-network is applied as base reinforcement learning algorithm 1. During the training, the UAV-BS explores the state space and performs Q-value iterations at each training episode. An 8-greedy exploration is applied when determining the action to take at the next time instance. The probability of exploration is given by parameter 8. The exploration probability specifies the likelihood that the agent will execute state exploration and choose actions at random. Otherwise, the agent will perform the action that is believed to yield the highest expected reward. The data for each training step is stored in a replay batch D. Specifically, each row of D contains the tuple (s _t, a _t, r _t, s _t+1) , namely, current state, action, reward and next state for a training step. Samples will then be randomly selected and used for Q value model updating.

Below is the section for performance evaluation.

In this section, the impact of the antenna configuration and 3-D location of the UAV-BS on the performance of MC users in terms of throughput and drop rate are firstly investigated by using the system-level simulation results. Then, the performance of the proposed reinforcement learning algorithm discussed in section about proposed ML algorithm are evaluated. The system-level simulation is performed by using a Matlab-based simulator. The data generated from the Matlab simulator is exported and used for the reinforcement learning model training, model inference, decision making, as well as the algorithm validation.

As to System Performance Analysis, the system model discussed in section about the considered use case and system model is considered. It is assumed that all BSs and users have two transmitting and two receiving antennas. Note that for the UAV-BS, it is assumed that the same antennas are used for both the wireless access and backhaul links. The maximum allowed transmit powers for a macro-BS, a UAV-BS and a user are configured as 46, 40, and 23 dBm, respectively. Due to space limitations, in this subsection, only the DL performance results are discussed, considering two different levels of traffic load in the system. However, both DL and UL feature metrics discussed in section about proposed framework and signalling procedure to enable ML in an IAB network architecture have been used when evaluating the proposed reinforcement learning algorithm.

To gain insights into the impact of UAV-BS antenna tilt and flying height on the considered performance metrics, the UAV-BS’s 2-D position is fixed in the center of the deployment map and the system performance in terms of the backhaul link rate, DL throughput and drop rate of MC users for different traffic load levels are investigated. It can be concluded that both UAV-BS antenna tilt and height have a considerable impact on the backhaul link rate, DL MC user throughput and MC user drop rate.

After investigating the UAV-BS position’s impact on interested performance metrics, it can be concluded that for a given performance metric, e.g., 5-percentile MC user throughput, the optimal UAV-BS 2-D location changes when the network traffic load level changes. In addition, the optimal UAV-BS position is different when considering different performance metrics, e.g., maximizing the 5-percentile MC user throughput, maximizing the 50-percentile MC user throughput, or minimizing the MC user drop rate. Therefore, the weights selected for different performance metrics in the reward function will impact the optimal location of the UAV-BS.

As to Reinforcement Learning Performance Evaluation, in this section, the results obtained through reinforcement learning algorithm proposed in Section about proposed ML algorithm are presented. The result of the algorithm is compared with the global optimal state, which is obtained by using grid search through the whole data set. The benefits of using the proposed algorithm and its ability to adapt to the changing wireless environment after model training are shown. During the training, the learning rate is set to 5e-5 and the number of training iterations equals 1500. The convergence of the algorithm during the model training may be firstly analyzed.

Based on the simulation results, for both the light load and heavy load cases, the proposed algorithm can learn from the history and eventually approaching the optimal state that gives the largest reward value in both load scenarios. The same conclusion can also be made by comparing the reward value column of Table II.

TABLE II COMPARISON OF THE AVERAGE VALUE OF THE SIX SYSTEM PERFORMANCE METRICS DURING UAV-BS DEPLOYMENT IN TWO LOAD SCENARIOS

After investigating the performance of the considered six feature metrics during a deployment, each of which contains 100 steps for a UAV-BS to make decisions and take action, it can be concluded that based on the past experience and a well-trained learning model, the proposed algorithm can quickly configure and navigate the UAV-BS to optimize the considered performance metrics, only 3-4 steps are needed for the UAV-BS to reach a stable state. As shown in Table II, the reward value (a weighted sum of the six considered performance metrics) achieved by the proposed reinforcement learning algorithm is only about 4%to 5%less than that provided by the global optimal solution for the light load and high load scenarios, respectively. Since the reward value summarizes the overall system performance metrics during the UAV-BS deployment, we, therefore, demonstrate the strength of the algorithm and the ability to provide fast connectivity to MC users in different traffic load scenarios.

Below is the section for conclusions and future work.

In this embodiment, a reinforcement learning algorithm to autonomously configure and navigate a UAV-BS to provide temporary wireless connectivity for MC users is developed. The UAV-BS is wirelessly connected to an on-ground donor BS and integrated into an existing mobile network using the 5G IAB technology. A functional framework and signalling procedure are proposed to support data collection, model training and decision making for the considered use case. An action encoding strategy is introduced to represent UAV-BS decisions considering multiple state dimensions, including the three-dimensional space location as well as the access and backhaul antenna electric tilt. The results demonstrate the benefits and efficiency of the proposed algorithm in different traffic load scenarios. The algorithm can help a UAV-BS quickly find the optimal 3-D location and its antenna configuration to provide a stable connection to MC users.

In the future work, different combinations of hyper-parameters and reward functions based on different service requirements may be investigated. Different alternatives of frameworks and signalling procedures to support applying centralized or distributed machine learning for the considered use case may be also studied.

As shown in FIG. 22 (a) , the apparatus 10 may comprise: at least one processor 101; and at least one memory 102. The at least one memory 102 contains instructions executable by the at least one processor 101. The apparatus 10 is operative for: collecting, by a data collection module, data about measurements and/or performance metrics relating to at least one terminal device to be served by at least one movable base station; determining, by a model inference module, configuration for deploying the at least one movable base station, based on at least part of the collected data; actuating, by an actor module, the at least one movable base station, based on at least the determined configuration.

In embodiments of the present disclosure, the apparatus 10 is further operative to perform the method according to any of the above embodiments, such as these shown in FIG. 5-21.

The processors 101 may be any kind of processing component, such as one or more microprocessor or microcontrollers, as well as other digital hardware, which may include digital signal processors (DSPs) , special-purpose digital logic, and the like. The memories 102 may be any kind of storage component, such as read-only memory (ROM) , random-access memory, cache memory, flash memory devices, optical storage devices, etc.

As shown in FIG. 22 (b) , the computer-readable storage medium 700, or any other kind of product, storing instructions 701 which when executed by at least one processor, cause the at least one processor to perform the method according to any one of the above embodiments, such as these shown in FIG. 5-21.

In addition, the present disclosure may also provide a carrier containing the computer program as mentioned above, wherein the carrier is one of an electronic signal, optical signal, radio signal, or computer readable storage medium. The computer readable storage medium can be, for example, an optical compact disk or an electronic memory device like a RAM (random access memory) , a ROM (read only memory) , Flash memory, magnetic tape, CD-ROM, DVD, Blue-ray disc and the like.

As shown in FIG. 23, the apparatus 10 for deploying movable base station in a communication network may comprise: a data collection module 8100, configured to collect data about measurements and/or performance metrics relating to at least one terminal device to be served by at least one movable base station; a model inference module 8101, configured to determine configuration for deploying the at least one movable base station, based on at least part of the collected data; an actor module 8102, configured to actuate the at least one movable base station, based on at least the determined configuration.

In embodiments of the present disclosure, the terminal device 100 is operative to perform the method according to any of the above embodiments, such as these shown in FIG. 5-21.

The term ‘module’ may have conventional meaning in the field of electronics, electrical devices and/or electronic devices and may include, for example, electrical and/or electronic circuitry, devices, modules, processors, memories, logic solid state and/or discrete devices, computer programs or instructions for carrying out respective tasks, procedures, computations, outputs, and/or displaying functions, and so on, as such as those that are described herein.

With these modules, the apparatus may not need a fixed processor or memory, any computing resource and storage resource may be arranged from at least one network node/device/entity/apparatus relating to the communication system. The virtualization technology and network computing technology (e.g. cloud computing) may be further introduced, so as to improve the usage efficiency of the network resources and the flexibility of the network.

The techniques described herein may be implemented by various means so that an apparatus implementing one or more functions of a corresponding apparatus described with an embodiment comprises not only prior art means, but also means for implementing the one or more functions of the corresponding apparatus described with the embodiment and it may comprise separate means for each separate function, or means that may be configured to perform two or more functions. For example, these techniques may be implemented in hardware (one or more apparatuses) , firmware (one or more apparatuses) , software (one or more modules) , or combinations thereof. For a firmware or software, implementation may be made through modules (e.g., procedures, functions, and so on) that perform the functions described herein.

Particularly, these function units may be implemented either as a network element on a dedicated hardware, as a software instance running on a dedicated hardware, or as a virtualized function instantiated on an appropriate platform, e.g. on a cloud infrastructure.

Although the subject matter described herein may be implemented in any appropriate type of system using any suitable components, the embodiments disclosed herein are described in relation to a wireless network, such as the example wireless network illustrated in FIG. 24. For simplicity, the wireless network of FIG. 24 only depicts network 1006, network nodes 1060 (corresponding to network node 200) and 1060b, and

WDs

1010, 1010b, and 1010c (corresponding to terminal device 100) . In practice, a wireless network may further include any additional elements suitable to support communication between wireless devices or between a wireless device and another communication device, such as a landline telephone, a service provider, or any other network node or end device. Of the illustrated components, network node 1060 and wireless device (WD) 1010 are depicted with additional detail. The wireless network may provide communication and other types of services to one or more wireless devices to facilitate the wireless devices’ access to and/or use of the services provided by, or via, the wireless network.

The wireless network may comprise and/or interface with any type of communication, telecommunication, data, cellular, and/or radio network or other similar type of system. In some embodiments, the wireless network may be configured to operate according to specific standards or other types of predefined rules or procedures. Thus, particular embodiments of the wireless network may implement communication standards, such as Global System for Mobile Communications (GSM) , Universal Mobile Telecommunications System (UMTS) , Long Term Evolution (LTE) , and/or other suitable 2G, 3G, 4G, or 5G standards; wireless local area network (WLAN) standards, such as the IEEE 802.11 standards; and/or any other appropriate wireless communication standard, such as the Worldwide Interoperability for Microwave Access (WiMax) , Bluetooth, Z-Wave and/or ZigBee standards.

Network 1006 may comprise one or more backhaul networks, core networks, IP networks, public switched telephone networks (PSTNs) , packet data networks, optical networks, wide-area networks (WANs) , local area networks (LANs) , wireless local area networks (WLANs) , wired networks, wireless networks, metropolitan area networks, and other networks to enable communication between devices.

Network node 1060 and WD 1010 comprise various components described in more detail below. These components work together in order to provide network node and/or wireless device functionality, such as providing wireless connections in a wireless network. In different embodiments, the wireless network may comprise any number of wired or wireless networks, network nodes, base stations, controllers, wireless devices, relay stations, and/or any other components or systems that may facilitate or participate in the communication of data and/or signals whether via wired or wireless connections.

As used herein, network node refers to equipment capable, configured, arranged and/or operable to communicate directly or indirectly with a wireless device and/or with other network nodes or equipment in the wireless network to enable and/or provide wireless access to the wireless device and/or to perform other functions (e.g., administration) in the wireless network. Examples of network nodes include, but are not limited to, access points (APs) (e.g., radio access points) , base stations (BSs) (e.g., radio base stations, Node Bs, evolved Node Bs (eNBs) and NR NodeBs (gNBs) ) . Base stations may be categorized based on the amount of coverage they provide (or, stated differently, their transmit power level) and may then also be referred to as femto base stations, pico base stations, micro base stations, or macro base stations. A base station may be a relay node or a relay donor node controlling a relay. A network node may also include one or more (or all) parts of a distributed radio base station such as centralized digital units and/or remote radio units (RRUs) , sometimes referred to as Remote Radio Heads (RRHs) . Such remote radio units may or may not be integrated with an antenna as an antenna integrated radio. Parts of a distributed radio base station may also be referred to as nodes in a distributed antenna system (DAS) . Yet further examples of network nodes include multi-standard radio (MSR) equipment such as MSR BSs, network controllers such as radio network controllers (RNCs) or base station controllers (BSCs) , base transceiver stations (BTSs) , transmission points, transmission nodes, multi-cell/multicast coordination entities (MCEs) , core network nodes (e.g., MSCs, MMEs) , O&M nodes, OSS nodes, SON nodes, positioning nodes (e.g., E-SMLCs) , and/or MDTs. As another example, a network node may be a virtual network node as described in more detail below. More generally, however, network nodes may represent any suitable device (or group of devices) capable, configured, arranged, and/or operable to enable and/or provide a wireless device with access to the wireless network or to provide some service to a wireless device that has accessed the wireless network.

In FIG. 24, network node 1060 includes processing circuitry 1070, device readable medium 1080, interface 1090, auxiliary equipment 1084, power source 1086, power circuitry 1087, and antenna 1062. Although network node 1060 illustrated in the example wireless network of FIG. 24 may represent a device that includes the illustrated combination of hardware components, other embodiments may comprise network nodes with different combinations of components. It is to be understood that a network node comprises any suitable combination of hardware and/or software needed to perform the tasks, features, functions and methods disclosed herein. Moreover, while the components of network node 1060 are depicted as single boxes located within a larger box, or nested within multiple boxes, in practice, a network node may comprise multiple different physical components that make up a single illustrated component (e.g., device readable medium 1080 may comprise multiple separate hard drives as well as multiple RAM modules) .

Similarly, network node 1060 may be composed of multiple physically separate components (e.g., a NodeB component and a RNC component, or a BTS component and a BSC component, etc. ) , which may each have their own respective components. In certain scenarios in which network node 1060 comprises multiple separate components (e.g., BTS and BSC components) , one or more of the separate components may be shared among several network nodes. For example, a single RNC may control multiple NodeB’s . In such a scenario, each unique NodeB and RNC pair, may in some instances be considered a single separate network node. In some embodiments, network node 1060 may be configured to support multiple radio access technologies (RATs) . In such embodiments, some components may be duplicated (e.g., separate device readable medium 1080 for the different RATs) and some components may be reused (e.g., the same antenna 1062 may be shared by the RATs) . Network node 1060 may also include multiple sets of the various illustrated components for different wireless technologies integrated into network node 1060, such as, for example, GSM, WCDMA, LTE, NR, WiFi, or Bluetooth wireless technologies. These wireless technologies may be integrated into the same or different chip or set of chips and other components within network node 1060.

Processing circuitry 1070 is configured to perform any determining, calculating, or similar operations (e.g., certain obtaining operations) described herein as being provided by a network node. These operations performed by processing circuitry 1070 may include processing information obtained by processing circuitry 1070 by, for example, converting the obtained information into other information, comparing the obtained information or converted information to information stored in the network node, and/or performing one or more operations based on the obtained information or converted information, and as a result of said processing making a determination.

Processing circuitry 1070 may comprise a combination of one or more of a microprocessor, controller, microcontroller, central processing unit, digital signal processor, application-specific integrated circuit, field programmable gate array, or any other suitable computing device, resource, or combination of hardware, software and/or encoded logic operable to provide, either alone or in conjunction with other network node 1060 components, such as device readable medium 1080, network node 1060 functionality. For example, processing circuitry 1070 may execute instructions stored in device readable medium 1080 or in memory within processing circuitry 1070. Such functionality may include providing any of the various wireless features, functions, or benefits discussed herein. In some embodiments, processing circuitry 1070 may include a system on a chip (SOC) .

In some embodiments, processing circuitry 1070 may include one or more of radio frequency (RF) transceiver circuitry 1072 and baseband processing circuitry 1074. In some embodiments, radio frequency (RF) transceiver circuitry 1072 and baseband processing circuitry 1074 may be on separate chips (or sets of chips) , boards, or units, such as radio units and digital units. In alternative embodiments, part or all of RF transceiver circuitry 1072 and baseband processing circuitry 1074 may be on the same chip or set of chips, boards, or units

In certain embodiments, some or all of the functionality described herein as being provided by a network node, base station, eNB or other such network device may be performed by processing circuitry 1070 executing instructions stored on device readable medium 1080 or memory within processing circuitry 1070. In alternative embodiments, some or all of the functionality may be provided by processing circuitry 1070 without executing instructions stored on a separate or discrete device readable medium, such as in a hard-wired manner. In any of those embodiments, whether executing instructions stored on a device readable storage medium or not, processing circuitry 1070 can be configured to perform the described functionality. The benefits provided by such functionality are not limited to processing circuitry 1070 alone or to other components of network node 1060, but are enjoyed by network node 1060 as a whole, and/or by end users and the wireless network generally.

Device readable medium 1080 may comprise any form of volatile or non-volatile computer readable memory including, without limitation, persistent storage, solid-state memory, remotely mounted memory, magnetic media, optical media, random access memory (RAM) , read-only memory (ROM) , mass storage media (for example, a hard disk) , removable storage media (for example, a flash drive, a Compact Disk (CD) or a Digital Video Disk (DVD) ) , and/or any other volatile or non-volatile, non-transitory device readable and/or computer-executable memory devices that store information, data, and/or instructions that may be used by processing circuitry 1070. Device readable medium 1080 may store any suitable instructions, data or information, including a computer program, software, an application including one or more of logic, rules, code, tables, etc. and/or other instructions capable of being executed by processing circuitry 1070 and, utilized by network node 1060. Device readable medium 1080 may be used to store any calculations made by processing circuitry 1070 and/or any data received via interface 1090. In some embodiments, processing circuitry 1070 and device readable medium 1080 may be considered to be integrated.

Interface 1090 is used in the wired or wireless communication of signalling and/or data between network node 1060, network 1006, and/or WDs 1010. As illustrated, interface 1090 comprises port (s) /terminal (s) 1094 to send and receive data, for example to and from network 1006 over a wired connection. Interface 1090 also includes radio front end circuitry 1092 that may be coupled to, or in certain embodiments a part of, antenna 1062. Radio front end circuitry 1092 comprises filters 1098 and amplifiers 1096. Radio front end circuitry 1092 may be connected to antenna 1062 and processing circuitry 1070. Radio front end circuitry may be configured to condition signals communicated between antenna 1062 and processing circuitry 1070. Radio front end circuitry 1092 may receive digital data that is to be sent out to other network nodes or WDs via a wireless connection. Radio front end circuitry 1092 may convert the digital data into a radio signal having the appropriate channel and bandwidth parameters using a combination of filters 1098 and/or amplifiers 1096. The radio signal may then be transmitted via antenna 1062. Similarly, when receiving data, antenna 1062 may collect radio signals which are then converted into digital data by radio front end circuitry 1092. The digital data may be passed to processing circuitry 1070. In other embodiments, the interface may comprise different components and/or different combinations of components.

In certain alternative embodiments, network node 1060 may not include separate radio front end circuitry 1092, instead, processing circuitry 1070 may comprise radio front end circuitry and may be connected to antenna 1062 without separate radio front end circuitry 1092. Similarly, in some embodiments, all or some of RF transceiver circuitry 1072 may be considered a part of interface 1090. In still other embodiments, interface 1090 may include one or more ports or terminals 1094, radio front end circuitry 1092, and RF transceiver circuitry 1072, as part of a radio unit (not shown) , and interface 1090 may communicate with baseband processing circuitry 1074, which is part of a digital unit (not shown) .

Antenna 1062 may include one or more antennas, or antenna arrays, configured to send and/or receive wireless signals. Antenna 1062 may be coupled to radio front end circuitry 1090 and may be any type of antenna capable of transmitting and receiving data and/or signals wirelessly. In some embodiments, antenna 1062 may comprise one or more omni-directional, sector or panel antennas operable to transmit/receive radio signals between, for example, 2 GHz and 66 GHz. An omni-directional antenna may be used to transmit/receive radio signals in any direction, a sector antenna may be used to transmit/receive radio signals from devices within a particular area, and a panel antenna may be a line of sight antenna used to transmit/receive radio signals in a relatively straight line. In some instances, the use of more than one antenna may be referred to as MIMO. In certain embodiments, antenna 1062 may be separate from network node 1060 and may be connectable to network node 1060 through an interface or port.

Antenna 1062, interface 1090, and/or processing circuitry 1070 may be configured to perform any receiving operations and/or certain obtaining operations described herein as being performed by a network node. Any information, data and/or signals may be received from a wireless device, another network node and/or any other network equipment. Similarly, antenna 1062, interface 1090, and/or processing circuitry 1070 may be configured to perform any transmitting operations described herein as being performed by a network node. Any information, data and/or signals may be transmitted to a wireless device, another network node and/or any other network equipment.

Power circuitry 1087 may comprise, or be coupled to, power management circuitry and is configured to supply the components of network node 1060 with power for performing the functionality described herein. Power circuitry 1087 may receive power from power source 1086. Power source 1086 and/or power circuitry 1087 may be configured to provide power to the various components of network node 1060 in a form suitable for the respective components (e.g., at a voltage and current level needed for each respective component) . Power source 1086 may either be included in, or external to, power circuitry 1087 and/or network node 1060. For example, network node 1060 may be connectable to an external power source (e.g., an electricity outlet) via an input circuitry or interface such as an electrical cable, whereby the external power source supplies power to power circuitry 1087. As a further example, power source 1086 may comprise a source of power in the form of a battery or battery pack which is connected to, or integrated in, power circuitry 1087. The battery may provide backup power should the external power source fail. Other types of power sources, such as photovoltaic devices, may also be used.

Alternative embodiments of network node 1060 may include additional components beyond those shown in FIG. 24 that may be responsible for providing certain aspects of the network node’s functionality, including any of the functionality described herein and/or any functionality necessary to support the subject matter described herein. For example, network node 1060 may include user interface equipment to allow input of information into network node 1060 and to allow output of information from network node 1060. This may allow a user to perform diagnostic, maintenance, repair, and other administrative functions for network node 1060.

As used herein, wireless device (WD) refers to a device capable, configured, arranged and/or operable to communicate wirelessly with network nodes and/or other wireless devices. Unless otherwise noted, the term WD may be used interchangeably herein with user equipment (UE) . Communicating wirelessly may involve transmitting and/or receiving wireless signals using electromagnetic waves, radio waves, infrared waves, and/or other types of signals suitable for conveying information through air. In some embodiments, a WD may be configured to transmit and/or receive information without direct human interaction. For instance, a WD may be designed to transmit information to a network on a predetermined schedule, when triggered by an internal or external event, or in response to requests from the network. Examples of a WD include, but are not limited to, a smart phone, a mobile phone, a cell phone, a voice over IP (VoIP) phone, a wireless local loop phone, a desktop computer, a personal digital assistant (PDA) , a wireless cameras, a gaming console or device, a music storage device, a playback appliance, a wearable terminal device, a wireless endpoint, a mobile station, a tablet, a laptop, a laptop-embedded equipment (LEE) , a laptop-mounted equipment (LME) , a smart device, a wireless customer-premise equipment (CPE) , a vehicle-mounted wireless terminal device, etc.. A WD may support device-to-device (D2D) communication, for example by implementing a 3GPP standard for sidelink communication, vehicle-to-vehicle (V2V) , vehicle-to-infrastructure (V2I) , vehicle-to-everything (V2X) and may in this case be referred to as a D2D communication device. As yet another specific example, in an Internet of Things (IoT) scenario, a WD may represent a machine or other device that performs monitoring and/or measurements, and transmits the results of such monitoring and/or measurements to another WD and/or a network node. The WD may in this case be a machine-to-machine (M2M) device, which may in a 3GPP context be referred to as an MTC device. As one particular example, the WD may be a UE implementing the 3GPP narrow band internet of things (NB-IoT) standard. Particular examples of such machines or devices are sensors, metering devices such as power meters, industrial machinery, or home or personal appliances (e.g. refrigerators, televisions, etc. ) personal wearables (e.g., watches, fitness trackers, etc. ) . In other scenarios, a WD may represent a vehicle or other equipment that is capable of monitoring and/or reporting on its operational status or other functions associated with its operation. A WD as described above may represent the endpoint of a wireless connection, in which case the device may be referred to as a wireless terminal. Furthermore, a WD as described above may be mobile, in which case it may also be referred to as a mobile device or a mobile terminal.

As illustrated, wireless device 1010 includes antenna 1011, interface 1014, processing circuitry 1020, device readable medium 1030, user interface equipment 1032, auxiliary equipment 1034, power source 1036 and power circuitry 1037. WD 1010 may include multiple sets of one or more of the illustrated components for different wireless technologies supported by WD 1010, such as, for example, GSM, WCDMA, LTE, NR, WiFi, WiMAX, or Bluetooth wireless technologies, just to mention a few. These wireless technologies may be integrated into the same or different chips or set of chips as other components within WD 1010.

Antenna 1011 may include one or more antennas or antenna arrays, configured to send and/or receive wireless signals, and is connected to interface 1014. In certain alternative embodiments, antenna 1011 may be separate from WD 1010 and be connectable to WD 1010 through an interface or port. Antenna 1011, interface 1014, and/or processing circuitry 1020 may be configured to perform any receiving or transmitting operations described herein as being performed by a WD. Any information, data and/or signals may be received from a network node and/or another WD. In some embodiments, radio front end circuitry and/or antenna 1011 may be considered an interface.

As illustrated, interface 1014 comprises radio front end circuitry 1012 and antenna 1011. Radio front end circuitry 1012 comprise one or more filters 1018 and amplifiers 1016. Radio front end circuitry 1014 is connected to antenna 1011 and processing circuitry 1020, and is configured to condition signals communicated between antenna 1011 and processing circuitry 1020. Radio front end circuitry 1012 may be coupled to or a part of antenna 1011. In some embodiments, WD 1010 may not include separate radio front end circuitry 1012; rather, processing circuitry 1020 may comprise radio front end circuitry and may be connected to antenna 1011. Similarly, in some embodiments, some or all of RF transceiver circuitry 1022 may be considered a part of interface 1014. Radio front end circuitry 1012 may receive digital data that is to be sent out to other network nodes or WDs via a wireless connection. Radio front end circuitry 1012 may convert the digital data into a radio signal having the appropriate channel and bandwidth parameters using a combination of filters 1018 and/or amplifiers 1016. The radio signal may then be transmitted via antenna 1011. Similarly, when receiving data, antenna 1011 may collect radio signals which are then converted into digital data by radio front end circuitry 1012. The digital data may be passed to processing circuitry 1020. In other embodiments, the interface may comprise different components and/or different combinations of components.

Processing circuitry 1020 may comprise a combination of one or more of a microprocessor, controller, microcontroller, central processing unit, digital signal processor, application-specific integrated circuit, field programmable gate array, or any other suitable computing device, resource, or combination of hardware, software, and/or encoded logic operable to provide, either alone or in conjunction with other WD 1010 components, such as device readable medium 1030, WD 1010 functionality. Such functionality may include providing any of the various wireless features or benefits discussed herein. For example, processing circuitry 1020 may execute instructions stored in device readable medium 1030 or in memory within processing circuitry 1020 to provide the functionality disclosed herein.

As illustrated, processing circuitry 1020 includes one or more of RF transceiver circuitry 1022, baseband processing circuitry 1024, and application processing circuitry 1026. In other embodiments, the processing circuitry may comprise different components and/or different combinations of components. In certain embodiments processing circuitry 1020 of WD 1010 may comprise a SOC. In some embodiments, RF transceiver circuitry 1022, baseband processing circuitry 1024, and application processing circuitry 1026 may be on separate chips or sets of chips. In alternative embodiments, part or all of baseband processing circuitry 1024 and application processing circuitry 1026 may be combined into one chip or set of chips, and RF transceiver circuitry 1022 may be on a separate chip or set of chips. In still alternative embodiments, part or all of RF transceiver circuitry 1022 and baseband processing circuitry 1024 may be on the same chip or set of chips, and application processing circuitry 1026 may be on a separate chip or set of chips. In yet other alternative embodiments, part or all of RF transceiver circuitry 1022, baseband processing circuitry 1024, and application processing circuitry 1026 may be combined in the same chip or set of chips. In some embodiments, RF transceiver circuitry 1022 may be a part of interface 1014. RF transceiver circuitry 1022 may condition RF signals for processing circuitry 1020.

In certain embodiments, some or all of the functionality described herein as being performed by a WD may be provided by processing circuitry 1020 executing instructions stored on device readable medium 1030, which in certain embodiments may be a computer-readable storage medium. In alternative embodiments, some or all of the functionality may be provided by processing circuitry 1020 without executing instructions stored on a separate or discrete device readable storage medium, such as in a hard-wired manner. In any of those particular embodiments, whether executing instructions stored on a device readable storage medium or not, processing circuitry 1020 can be configured to perform the described functionality. The benefits provided by such functionality are not limited to processing circuitry 1020 alone or to other components of WD 1010, but are enjoyed by WD 1010 as a whole, and/or by end users and the wireless network generally.

Processing circuitry 1020 may be configured to perform any determining, calculating, or similar operations (e.g., certain obtaining operations) described herein as being performed by a WD. These operations, as performed by processing circuitry 1020, may include processing information obtained by processing circuitry 1020 by, for example, converting the obtained information into other information, comparing the obtained information or converted information to information stored by WD 1010, and/or performing one or more operations based on the obtained information or converted information, and as a result of said processing making a determination.

Device readable medium 1030 may be operable to store a computer program, software, an application including one or more of logic, rules, code, tables, etc. and/or other instructions capable of being executed by processing circuitry 1020. Device readable medium 1030 may include computer memory (e.g., Random Access Memory (RAM) or Read Only Memory (ROM) ) , mass storage media (e.g., a hard disk) , removable storage media (e.g., a Compact Disk (CD) or a Digital Video Disk (DVD) ) , and/or any other volatile or non-volatile, non-transitory device readable and/or computer executable memory devices that store information, data, and/or instructions that may be used by processing circuitry 1020. In some embodiments, processing circuitry 1020 and device readable medium 1030 may be considered to be integrated.

User interface equipment 1032 may provide components that allow for a human user to interact with WD 1010. Such interaction may be of many forms, such as visual, audial, tactile, etc. User interface equipment 1032 may be operable to produce output to the user and to allow the user to provide input to WD 1010. The type of interaction may vary depending on the type of user interface equipment 1032 installed in WD 1010. For example, if WD 1010 is a smart phone, the interaction may be via a touch screen; if WD 1010 is a smart meter, the interaction may be through a screen that provides usage (e.g., the number of gallons used) or a speaker that provides an audible alert (e.g., if smoke is detected) . User interface equipment 1032 may include input interfaces, devices and circuits, and output interfaces, devices and circuits. User interface equipment 1032 is configured to allow input of information into WD 1010, and is connected to processing circuitry 1020 to allow processing circuitry 1020 to process the input information. User interface equipment 1032 may include, for example, a microphone, a proximity or other sensor, keys/buttons, a touch display, one or more cameras, a USB port, or other input circuitry. User interface equipment 1032 is also configured to allow output of information from WD 1010, and to allow processing circuitry 1020 to output information from WD 1010. User interface equipment 1032 may include, for example, a speaker, a display, vibrating circuitry, a USB port, a headphone interface, or other output circuitry. Using one or more input and output interfaces, devices, and circuits, of user interface equipment 1032, WD 1010 may communicate with end users and/or the wireless network, and allow them to benefit from the functionality described herein.

Auxiliary equipment 1034 is operable to provide more specific functionality which may not be generally performed by WDs. This may comprise specialized sensors for doing measurements for various purposes, interfaces for additional types of communication such as wired communications etc. The inclusion and type of components of auxiliary equipment 1034 may vary depending on the embodiment and/or scenario.

Power source 1036 may, in some embodiments, be in the form of a battery or battery pack. Other types of power sources, such as an external power source (e.g., an electricity outlet) , photovoltaic devices or power cells, may also be used. WD 1010 may further comprise power circuitry 1037 for delivering power from power source 1036 to the various parts of WD 1010 which need power from power source 1036 to carry out any functionality described or indicated herein. Power circuitry 1037 may in certain embodiments comprise power management circuitry. Power circuitry 1037 may additionally or alternatively be operable to receive power from an external power source; in which case WD 1010 may be connectable to the external power source (such as an electricity outlet) via input circuitry or an interface such as an electrical power cable. Power circuitry 1037 may also in certain embodiments be operable to deliver power from an external power source to power source 1036. This may be, for example, for the charging of power source 1036. Power circuitry 1037 may perform any formatting, converting, or other modification to the power from power source 1036 to make the power suitable for the respective components of WD 1010 to which power is supplied.

FIG. 25 illustrates one embodiment of a UE in accordance with various aspects described herein. As used herein, a user equipment or UE may not necessarily have a user in the sense of a human user who owns and/or operates the relevant device. Instead, a UE may represent a device that is intended for sale to, or operation by, a human user but which may not, or which may not initially, be associated with a specific human user (e.g., a smart sprinkler controller) . Alternatively, a UE may represent a device that is not intended for sale to, or operation by, an end user but which may be associated with or operated for the benefit of a user (e.g., a smart power meter) . UE 1100 may be any UE identified by the 3 ^rd Generation Partnership Project (3GPP) , including a NB-IoT UE, a machine type communication (MTC) UE, and/or an enhanced MTC (eMTC) UE. UE 1100, as illustrated in FIG. 25, is one example of a WD configured for communication in accordance with one or more communication standards promulgated by the 3 ^rd Generation Partnership Project (3GPP) , such as 3GPP’s GSM, UMTS, LTE, and/or 5G standards. As mentioned previously, the term WD and UE may be used interchangeable. Accordingly, although FIG. 25 is a UE, the components discussed herein are equally applicable to a WD, and vice-versa.

In FIG. 25, UE 1100 includes processing circuitry 1101 that is operatively coupled to input/output interface 1105, radio frequency (RF) interface 1109, network connection interface 1111, memory 1115 including random access memory (RAM) 1117, read-only memory (ROM) 1119, and storage medium 1121 or the like, communication subsystem 1131, power source 1133, and/or any other component, or any combination thereof. Storage medium 1121 includes operating system 1123, application program 1125, and data 1127. In other embodiments, storage medium 1121 may include other similar types of information. Certain UEs may utilize all of the components shown in FIG. 25, or only a subset of the components. The level of integration between the components may vary from one UE to another UE. Further, certain UEs may contain multiple instances of a component, such as multiple processors, memories, transceivers, transmitters, receivers, etc.

In FIG. 25, processing circuitry 1101 may be configured to process computer instructions and data. Processing circuitry 1101 may be configured to implement any sequential state machine operative to execute machine instructions stored as machine-readable computer programs in the memory, such as one or more hardware-implemented state machines (e.g., in discrete logic, FPGA, ASIC, etc. ) ; programmable logic together with appropriate firmware; one or more stored program, general-purpose processors, such as a microprocessor or Digital Signal Processor (DSP) , together with appropriate software; or any combination of the above. For example, the processing circuitry 1101 may include two central processing units (CPUs) . Data may be information in a form suitable for use by a computer.

In the depicted embodiment, input/output interface 1105 may be configured to provide a communication interface to an input device, output device, or input and output device. UE 1100 may be configured to use an output device via input/output interface 1105. An output device may use the same type of interface port as an input device. For example, a USB port may be used to provide input to and output from UE 1100. The output device may be a speaker, a sound card, a video card, a display, a monitor, a printer, an actuator, an emitter, a smartcard, another output device, or any combination thereof. UE 1100 may be configured to use an input device via input/output interface 1105 to allow a user to capture information into UE 1100. The input device may include a touch-sensitive or presence-sensitive display, a camera (e.g., a digital camera, a digital video camera, a web camera, etc. ) , a microphone, a sensor, a mouse, a trackball, a directional pad, a trackpad, a scroll wheel, a smartcard, and the like. The presence-sensitive display may include a capacitive or resistive touch sensor to sense input from a user. A sensor may be, for instance, an accelerometer, a gyroscope, a tilt sensor, a force sensor, a magnetometer, an optical sensor, a proximity sensor, another like sensor, or any combination thereof. For example, the input device may be an accelerometer, a magnetometer, a digital camera, a microphone, and an optical sensor.

In FIG. 25, RF interface 1109 may be configured to provide a communication interface to RF components such as a transmitter, a receiver, and an antenna. Network connection interface 1111 may be configured to provide a communication interface to network 1143a. Network 1143a may encompass wired and/or wireless networks such as a local-area network (LAN) , a wide-area network (WAN) , a computer network, a wireless network, a telecommunications network, another like network or any combination thereof. For example, network 1143a may comprise a Wi-Fi network. Network connection interface 1111 may be configured to include a receiver and a transmitter interface used to communicate with one or more other devices over a communication network according to one or more communication protocols, such as Ethernet, TCP/IP, SONET, ATM, or the like. Network connection interface 1111 may implement receiver and transmitter functionality appropriate to the communication network links (e.g., optical, electrical, and the like) . The transmitter and receiver functions may share circuit components, software or firmware, or alternatively may be implemented separately.

RAM 1117 may be configured to interface via bus 1102 to processing circuitry 1101 to provide storage or caching of data or computer instructions during the execution of software programs such as the operating system, application programs, and device drivers. ROM 1119 may be configured to provide computer instructions or data to processing circuitry 1101. For example, ROM 1119 may be configured to store invariant low-level system code or data for basic system functions such as basic input and output (I/O) , startup, or reception of keystrokes from a keyboard that are stored in a non-volatile memory. Storage medium 1121 may be configured to include memory such as RAM, ROM, programmable read-only memory (PROM) , erasable programmable read-only memory (EPROM) , electrically erasable programmable read-only memory (EEPROM) , magnetic disks, optical disks, floppy disks, hard disks, removable cartridges, or flash drives. In one example, storage medium 1121 may be configured to include operating system 1123, application program 1125 such as a web browser application, a widget or gadget engine or another application, and data file 1127. Storage medium 1121 may store, for use by UE 1100, any of a variety of various operating systems or combinations of operating systems.

Storage medium 1121 may be configured to include a number of physical drive units, such as redundant array of independent disks (RAID) , floppy disk drive, flash memory, USB flash drive, external hard disk drive, thumb drive, pen drive, key drive, high-density digital versatile disc (HD-DVD) optical disc drive, internal hard disk drive, Blu-Ray optical disc drive, holographic digital data storage (HDDS) optical disc drive, external mini-dual in-line memory module (DIMM) , synchronous dynamic random access memory (SDRAM) , external micro-DIMM SDRAM, smartcard memory such as a subscriber identity module or a removable user identity (SIM/RUIM) module, other memory, or any combination thereof. Storage medium 1121 may allow UE 1100 to access computer-executable instructions, application programs or the like, stored on transitory or non-transitory memory media, to off-load data, or to upload data. An article of manufacture, such as one utilizing a communication system may be tangibly embodied in storage medium 1121, which may comprise a device readable medium.

In FIG. 25, processing circuitry 1101 may be configured to communicate with network 1143b using communication subsystem 1131. Network 1143a and network 1143b may be the same network or networks or different network or networks. Communication subsystem 1131 may be configured to include one or more transceivers used to communicate with network 1143b. For example, communication subsystem 1131 may be configured to include one or more transceivers used to communicate with one or more remote transceivers of another device capable of wireless communication such as another WD, UE, or base station of a radio access network (RAN) according to one or more communication protocols, such as IEEE 802.11, CDMA, WCDMA, GSM, LTE, UTRAN, WiMax, or the like. Each transceiver may include transmitter 1133 and/or receiver 1135 to implement transmitter or receiver functionality, respectively, appropriate to the RAN links (e.g., frequency allocations and the like) . Further, transmitter 1133 and receiver 1135 of each transceiver may share circuit components, software or firmware, or alternatively may be implemented separately.

In the illustrated embodiment, the communication functions of communication subsystem 1131 may include data communication, voice communication, multimedia communication, short-range communications such as Bluetooth, near-field communication, location-based communication such as the use of the global positioning system (GPS) to determine a location, another like communication function, or any combination thereof. For example, communication subsystem 1131 may include cellular communication, Wi-Fi communication, Bluetooth communication, and GPS communication. Network 1143b may encompass wired and/or wireless networks such as a local-area network (LAN) , a wide-area network (WAN) , a computer network, a wireless network, a telecommunications network, another like network or any combination thereof. For example, network 1143b may be a cellular network, a Wi-Fi network, and/or a near-field network. Power source 1113 may be configured to provide alternating current (AC) or direct current (DC) power to components of UE 1100.

The features, benefits and/or functions described herein may be implemented in one of the components of UE 1100 or partitioned across multiple components of UE 1100. Further, the features, benefits, and/or functions described herein may be implemented in any combination of hardware, software or firmware. In one example, communication subsystem 1131 may be configured to include any of the components described herein. Further, processing circuitry 1101 may be configured to communicate with any of such components over bus 1102. In another example, any of such components may be represented by program instructions stored in memory that when executed by processing circuitry 1101 perform the corresponding functions described herein. In another example, the functionality of any of such components may be partitioned between processing circuitry 1101 and communication subsystem 1131. In another example, the non-computationally intensive functions of any of such components may be implemented in software or firmware and the computationally intensive functions may be implemented in hardware.

FIG. 26 is a schematic block diagram illustrating a virtualization environment 1200 in which functions implemented by some embodiments may be virtualized. In the present context, virtualizing means creating virtual versions of apparatuses or devices which may include virtualizing hardware platforms, storage devices and networking resources. As used herein, virtualization can be applied to a node (e.g., a virtualized base station or a virtualized radio access node) or to a device (e.g., a UE, a wireless device or any other type of communication device) or components thereof and relates to an implementation in which at least a portion of the functionality is implemented as one or more virtual components (e.g., via one or more applications, components, functions, virtual machines or containers executing on one or more physical processing nodes in one or more networks) .

In some embodiments, some or all of the functions described herein may be implemented as virtual components executed by one or more virtual machines implemented in one or more virtual environments 1200 hosted by one or more of hardware nodes 1230. Further, in embodiments in which the virtual node is not a radio access node or does not require radio connectivity (e.g., a core network node) , then the network node may be entirely virtualized.

The functions may be implemented by one or more applications 1220 (which may alternatively be called software instances, virtual appliances, network functions, virtual nodes, virtual network functions, etc. ) operative to implement some of the features, functions, and/or benefits of some of the embodiments disclosed herein. Applications 1220 are run in virtualization environment 1200 which provides hardware 1230 comprising processing circuitry 1260 and memory 1290. Memory 1290 contains instructions 1295 executable by processing circuitry 1260 whereby application 1220 is operative to provide one or more of the features, benefits, and/or functions disclosed herein.

Virtualization environment 1200, comprises general-purpose or special-purpose network hardware devices 1230 comprising a set of one or more processors or processing circuitry 1260, which may be commercial off-the-shelf (COTS) processors, dedicated Application Specific Integrated Circuits (ASICs) , or any other type of processing circuitry including digital or analog hardware components or special purpose processors. Each hardware device may comprise memory 1290-1 which may be non-persistent memory for temporarily storing instructions 1295 or software executed by processing circuitry 1260. Each hardware device may comprise one or more network interface controllers (NICs) 1270, also known as network interface cards, which include physical network interface 1280. Each hardware device may also include non-transitory, persistent, machine-readable storage media 1290-2 having stored therein software 1295 and/or instructions executable by processing circuitry 1260. Software 1295 may include any type of software including software for instantiating one or more virtualization layers 1250 (also referred to as hypervisors) , software to execute virtual machines 1240 as well as software allowing it to execute functions, features and/or benefits described in relation with some embodiments described herein.

Virtual machines 1240, comprise virtual processing, virtual memory, virtual networking or interface and virtual storage, and may be run by a corresponding virtualization layer 1250 or hypervisor. Different embodiments of the instance of virtual appliance 1220 may be implemented on one or more of virtual machines 1240, and the implementations may be made in different ways.

During operation, processing circuitry 1260 executes software 1295 to instantiate the hypervisor or virtualization layer 1250, which may sometimes be referred to as a virtual machine monitor (VMM) . Virtualization layer 1250 may present a virtual operating platform that appears like networking hardware to virtual machine 1240.

As shown in FIG. 26, hardware 1230 may be a standalone network node with generic or specific components. Hardware 1230 may comprise antenna 12225 and may implement some functions via virtualization. Alternatively, hardware 1230 may be part of a larger cluster of hardware (e.g. such as in a data center or customer premise equipment (CPE) ) where many hardware nodes work together and are managed via management and orchestration (MANO) 12100, which, among others, oversees lifecycle management of applications 1220.

Virtualization of the hardware is in some contexts referred to as network function virtualization (NFV) . NFV may be used to consolidate many network equipment types onto industry standard high volume server hardware, physical switches, and physical storage, which can be located in data centers, and customer premise equipment.

In the context of NFV, virtual machine 1240 may be a software implementation of a physical machine that runs programs as if they were executing on a physical, non-virtualized machine. Each of virtual machines 1240, and that part of hardware 1230 that executes that virtual machine, be it hardware dedicated to that virtual machine and/or hardware shared by that virtual machine with others of the virtual machines 1240, forms a separate virtual network elements (VNE) .

Still in the context of NFV, Virtual Network Function (VNF) is responsible for handling specific network functions that run in one or more virtual machines 1240 on top of hardware networking infrastructure 1230 and corresponds to application 1220 in FIG. 26.

In some embodiments, one or more radio units 12200 that each include one or more transmitters 12220 and one or more receivers 12210 may be coupled to one or more antennas 12225. Radio units 12200 may communicate directly with hardware nodes 1230 via one or more appropriate network interfaces and may be used in combination with the virtual components to provide a virtual node with radio capabilities, such as a radio access node or a base station.

In some embodiments, some signalling can be effected with the use of control system 12230 which may alternatively be used for communication between the hardware nodes 1230 and radio units 12200.

With reference to FIG. 27, in accordance with an embodiment, a communication system includes telecommunication network 1310, such as a 3GPP-type cellular network, which comprises access network 1311, such as a radio access network, and core network 1314. Access network 1311 comprises a plurality of

base stations

1312a, 1312b, 1312c, such as NBs, eNBs, gNBs or other types of wireless access points, each defining a

corresponding coverage area

1313a, 1313b, 1313c. Each

base station

1312a, 1312b, 1312c is connectable to core network 1314 over a wired or wireless connection 1315. A first UE 1391 located in coverage area 1313c is configured to wirelessly connect to, or be paged by, the corresponding base station 1312c. A second UE 1392 in coverage area 1313a is wirelessly connectable to the corresponding base station 1312a. While a plurality of

UEs

1391, 1392 are illustrated in this example, the disclosed embodiments are equally applicable to a situation where a sole UE is in the coverage area or where a sole UE is connecting to the corresponding base station 1312.

Telecommunication network 1310 is itself connected to host computer 1330, which may be embodied in the hardware and/or software of a standalone server, a cloud-implemented server, a distributed server or as processing resources in a server farm. Host computer 1330 may be under the ownership or control of a service provider, or may be operated by the service provider or on behalf of the service provider.

Connections

1321 and 1322 between telecommunication network 1310 and host computer 1330 may extend directly from core network 1314 to host computer 1330 or may go via an optional intermediate network 1320. Intermediate network 1320 may be one of, or a combination of more than one of, a public, private or hosted network; intermediate network 1320, if any, may be a backbone network or the Internet; in particular, intermediate network 1320 may comprise two or more sub-networks (not shown) .

The communication system of FIG. 27 as a whole enables connectivity between the connected

UEs

1391, 1392 and host computer 1330. The connectivity may be described as an over-the-top (OTT) connection 1350. Host computer 1330 and the connected

UEs

1391, 1392 are configured to communicate data and/or signaling via OTT connection 1350, using access network 1311, core network 1314, any intermediate network 1320 and possible further infrastructure (not shown) as intermediaries. OTT connection 1350 may be transparent in the sense that the participating communication devices through which OTT connection 1350 passes are unaware of routing of uplink and downlink communications. For example, base station 1312 may not or need not be informed about the past routing of an incoming downlink communication with data originating from host computer 1330 to be forwarded (e.g., handed over) to a connected UE 1391. Similarly, base station 1312 need not be aware of the future routing of an outgoing uplink communication originating from the UE 1391 towards the host computer 1330.

Example implementations, in accordance with an embodiment, of the UE, base station and host computer discussed in the preceding paragraphs will now be described with reference to FIG. 28. In communication system 1400, host computer 1410 comprises hardware 1415 including communication interface 1416 configured to set up and maintain a wired or wireless connection with an interface of a different communication device of communication system 1400. Host computer 1410 further comprises processing circuitry 1418, which may have storage and/or processing capabilities. In particular, processing circuitry 1418 may comprise one or more programmable processors, application-specific integrated circuits, field programmable gate arrays or combinations of these (not shown) adapted to execute instructions. Host computer 1410 further comprises software 1411, which is stored in or accessible by host computer 1410 and executable by processing circuitry 1418. Software 1411 includes host application 1412. Host application 1412 may be operable to provide a service to a remote user, such as UE 1430 connecting via OTT connection 1450 terminating at UE 1430 and host computer 1410. In providing the service to the remote user, host application 1412 may provide user data which is transmitted using OTT connection 1450.

Communication system 1400 further includes base station 1420 provided in a telecommunication system and comprising hardware 1425 enabling it to communicate with host computer 1410 and with UE 1430. Hardware 1425 may include communication interface 1426 for setting up and maintaining a wired or wireless connection with an interface of a different communication device of communication system 1400, as well as radio interface 1427 for setting up and maintaining at least wireless connection 1470 with UE 1430 located in a coverage area (not shown in FIG. 28) served by base station 1420. Communication interface 1426 may be configured to facilitate connection 1460 to host computer 1410. Connection 1460 may be direct or it may pass through a core network (not shown in FIG. 28) of the telecommunication system and/or through one or more intermediate networks outside the telecommunication system. In the embodiment shown, hardware 1425 of base station 1420 further includes processing circuitry 1428, which may comprise one or more programmable processors, application-specific integrated circuits, field programmable gate arrays or combinations of these (not shown) adapted to execute instructions. Base station 1420 further has software 1421 stored internally or accessible via an external connection.

Communication system 1400 further includes UE 1430 already referred to. Its hardware 1435 may include radio interface 1437 configured to set up and maintain wireless connection 1470 with a base station serving a coverage area in which UE 1430 is currently located. Hardware 1435 of UE 1430 further includes processing circuitry 1438, which may comprise one or more programmable processors, application-specific integrated circuits, field programmable gate arrays or combinations of these (not shown) adapted to execute instructions. UE 1430 further comprises software 1431, which is stored in or accessible by UE 1430 and executable by processing circuitry 1438. Software 1431 includes client application 1432. Client application 1432 may be operable to provide a service to a human or non-human user via UE 1430, with the support of host computer 1410. In host computer 1410, an executing host application 1412 may communicate with the executing client application 1432 via OTT connection 1450 terminating at UE 1430 and host computer 1410. In providing the service to the user, client application 1432 may receive request data from host application 1412 and provide user data in response to the request data. OTT connection 1450 may transfer both the request data and the user data. Client application 1432 may interact with the user to generate the user data that it provides.

It is noted that host computer 1410, base station 1420 and UE 1430 illustrated in FIG. 33 may be similar or identical to host computer 1330, one of

base stations

1312a, 1312b, 1312c and one of

UEs

1391, 1392 of FIG. 27, respectively. This is to say, the inner workings of these entities may be as shown in FIG. 28 and independently, the surrounding network topology may be that of FIG. 27.

In FIG. 28, OTT connection 1450 has been drawn abstractly to illustrate the communication between host computer 1410 and UE 1430 via base station 1420, without explicit reference to any intermediary devices and the precise routing of messages via these devices. Network infrastructure may determine the routing, which it may be configured to hide from UE 1430 or from the service provider operating host computer 1410, or both. While OTT connection 1450 is active, the network infrastructure may further take decisions by which it dynamically changes the routing (e.g., on the basis of load balancing consideration or reconfiguration of the network) .

Wireless connection 1470 between UE 1430 and base station 1420 is in accordance with the teachings of the embodiments described throughout this disclosure. One or more of the various embodiments improve the performance of OTT services provided to UE 1430 using OTT connection 1450, in which wireless connection 1470 forms the last segment. More precisely, the teachings of these embodiments may improve the latency, and power consumption for a reactivation of the network connection, and thereby provide benefits, such as reduced user waiting time, enhanced rate control.

A measurement procedure may be provided for the purpose of monitoring data rate, latency and other factors on which the one or more embodiments improve. There may further be an optional network functionality for reconfiguring OTT connection 1450 between host computer 1410 and UE 1430, in response to variations in the measurement results. The measurement procedure and/or the network functionality for reconfiguring OTT connection 1450 may be implemented in software 1411 and hardware 1415 of host computer 1410 or in software 1431 and hardware 1435 of UE 1430, or both. In embodiments, sensors (not shown) may be deployed in or in association with communication devices through which OTT connection 1450 passes; the sensors may participate in the measurement procedure by supplying values of the monitored quantities exemplified above, or supplying values of other physical quantities from which

software

1411, 1431 may compute or estimate the monitored quantities. The reconfiguring of OTT connection 1450 may include message format, retransmission settings, preferred routing etc.; the reconfiguring need not affect base station 1420, and it may be unknown or imperceptible to base station 1420. Such procedures and functionalities may be known and practiced in the art. In certain embodiments, measurements may involve proprietary UE signaling facilitating host computer 1410’s measurements of throughput, propagation times, latency and the like. The measurements may be implemented in that

software

1411 and 1431 causes messages to be transmitted, in particular empty or ‘dummy’ messages, using OTT connection 1450 while it monitors propagation times, errors etc.

The communication system includes a host computer, a base station and a UE which may be those described with reference to FIG. 27 and 28. For simplicity of the present disclosure, only drawing references to FIG. 29 will be included in this section. In step 1510, the host computer provides user data. In substep 1511 (which may be optional) of step 1510, the host computer provides the user data by executing a host application. In step 1520, the host computer initiates a transmission carrying the user data to the UE. In step 1530 (which may be optional) , the base station transmits to the UE the user data which was carried in the transmission that the host computer initiated, in accordance with the teachings of the embodiments described throughout this disclosure. In step 1540 (which may also be optional) , the UE executes a client application associated with the host application executed by the host computer.

The communication system includes a host computer, a base station and a UE which may be those described with reference to FIG. 27 and 28. For simplicity of the present disclosure, only drawing references to FIG. 30 will be included in this section. In step 1610 of the method, the host computer provides user data. In an optional substep (not shown) the host computer provides the user data by executing a host application. In step 1620, the host computer initiates a transmission carrying the user data to the UE. The transmission may pass via the base station, in accordance with the teachings of the embodiments described throughout this disclosure. In step 1630 (which may be optional) , the UE receives the user data carried in the transmission.

The communication system includes a host computer, a base station and a UE which may be those described with reference to FIG. 27 and 28. For simplicity of the present disclosure, only drawing references to FIG. 31 will be included in this section. In step 1710 (which may be optional) , the UE receives input data provided by the host computer. Additionally or alternatively, in step 1720, the UE provides user data. In substep 1721 (which may be optional) of step 1720, the UE provides the user data by executing a client application. In substep 1711 (which may be optional) of step 1710, the UE executes a client application which provides the user data in reaction to the received input data provided by the host computer. In providing the user data, the executed client application may further consider user input received from the user. Regardless of the specific manner in which the user data was provided, the UE initiates, in substep 1730 (which may be optional) , transmission of the user data to the host computer. In step 1740 of the method, the host computer receives the user data transmitted from the UE, in accordance with the teachings of the embodiments described throughout this disclosure.

The communication system includes a host computer, a base station and a UE which may be those described with reference to FIG. 27 and 28. For simplicity of the present disclosure, only drawing references to FIG. 32 will be included in this section. In step 1810 (which may be optional) , in accordance with the teachings of the embodiments described throughout this disclosure, the base station receives user data from the UE. In step 1820 (which may be optional) , the base station initiates transmission of the received user data to the host computer. In step 1830 (which may be optional) , the host computer receives the user data carried in the transmission initiated by the base station.

In general, the various exemplary embodiments of the present disclosure may be implemented in hardware or special purpose circuits, software, logic or any combination thereof. For example, some aspects may be implemented in hardware, while other aspects may be implemented in firmware or software that may be executed by a controller, microprocessor or other computing device, although the disclosure is not limited thereto. While various aspects of the exemplary embodiments of this disclosure may be illustrated and described as block diagrams, flow charts, or using some other pictorial representation, it is well understood that these blocks, apparatus, systems, techniques or methods described herein may be implemented in, as non-limiting examples, hardware, software, firmware, special purpose circuits or logic, general purpose hardware or controller or other computing devices, or some combination thereof.

As such, it should be appreciated that at least some aspects of the exemplary embodiments of the disclosure may be practiced in various components such as integrated circuit chips and modules. It should thus be appreciated that the exemplary embodiments of this disclosure may be realized in an apparatus that is embodied as an integrated circuit, where the integrated circuit may include circuitry (as well as possibly firmware) for embodying at least one or more of a data processor, a digital signal processor, baseband circuitry and radio frequency circuitry that are configurable so as to operate in accordance with the exemplary embodiments of this disclosure.

It should be appreciated that at least some aspects of the exemplary embodiments of the disclosure may be embodied in computer-executable instructions, such as in one or more program modules, executed by one or more computers or other devices. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types when executed by a processor in a computer or other device. The computer executable instructions may be stored on a computer readable medium such as a hard disk, optical disk, removable storage media, solid state memory, RAM, etc. As will be appreciated by those skilled in the art, the functionality of the program modules may be combined or distributed as desired in various embodiments. In addition, the functionality may be embodied in whole or in part in firmware or hardware equivalents such as integrated circuits, field programmable gate arrays (FPGA) , and the like.

The present disclosure includes any novel feature or combination of features disclosed herein either explicitly or any generalization thereof. Various modifications and adaptations to the foregoing exemplary embodiments of this disclosure may become apparent to those skilled in the relevant arts in view of the foregoing description, when read in conjunction with the accompanying drawings. However, any and all modifications will still fall within the scope of the non-limiting and exemplary embodiments of this disclosure.

Exemplary embodiments herein have been described above with reference to block diagrams and flowchart illustrations of methods and apparatuses. It will be understood that each block of the block diagrams and flowchart illustrations, and combinations of blocks in the block diagrams and flowchart illustrations, respectively, can be implemented by various means including computer program instructions. These computer program instructions may be loaded onto a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions which execute on the computer or other programmable data processing apparatus create means for implementing the functions specified in the flowchart block or blocks.

Further, while operations are depicted in a particular order, this should not be understood as requiring that such operations be performed in the particular order shown or in sequential order, or that all illustrated operations be performed, to achieve desirable results. In certain circumstances, multitasking and parallel processing may be advantageous. Likewise, while several specific implementation details are contained in the above discussions, these should not be construed as limitations on the scope of the subject matter described herein, but rather as descriptions of features that may be specific to particular embodiments. Certain features that are described in the context of separate embodiments may also be implemented in combination in a single embodiment. Conversely, various features that are described in the context of a single embodiment may also be implemented in multiple embodiments separately or in any suitable sub-combination.

While this specification contains many specific implementation details, these should not be construed as limitations on the scope of any implementation or of what may be claimed, but rather as descriptions of features that may be specific to particular embodiments of particular implementations. Certain features that are described in this specification in the context of separate embodiments can also be implemented in combination in a single embodiment. Conversely, various features that are described in the context of a single embodiment can also be implemented in multiple embodiments separately or in any suitable sub-combination. Moreover, although features may be described above as acting in certain combinations and even initially claimed as such, one or more features from a claimed combination can in some cases be excised from the combination, and the claimed combination may be directed to a sub-combination or variation of a sub-combination.

It will be obvious to a person skilled in the art that, as the technology advances, the inventive concept can be implemented in various ways. The above described embodiments are given for describing rather than limiting the disclosure, and it is to be understood that modifications and variations may be resorted to without departing from the spirit and scope of the disclosure as those skilled in the art readily understand. Such modifications and variations are considered to be within the scope of the disclosure and the appended claims. The protection scope of the disclosure is defined by the accompanying claims.

REFERENCES

[1] J. Li, K.K. Nagalapur, E. Stare, S. Dwivedi, S.A. Ashraf, P. -E. Eriksson, U. Engstro¨m, W. Lee, and T. Lohmar, “5G New Radio for Public Safety Mission Critical Communications, ” arXiv preprint arXiv: 2103.02434, 2021.

[2] S.A.R. Naqvi, S.A. Hassan, H. Pervaiz, and Q. Ni, “Drone-aided communication as a key enabler for 5G and resilient public safety networks, ” IEEE Communications Magazine, vol. 56, no. 1, pp. 36–42, 2018.

[3] K.P. Morison and J. Calahorrano. (2020) FirstNet Case Study: How FirstNet Deployables are Supporting Public Safety. [Online] . Available: https: //www. policeforum. org/assets/FirstNetDeployables. pdf

[4] A. Merwaday, A. Tuncer, A. Kumbhar, and I. Guvenc, “Improved throughput coverage in natural disasters: Unmanned aerial base stations for public-safety communications, ” IEEE Vehicular Technology Magazine, vol. 11, no. 4, pp. 53–60, 2016.

[5] L. Ferranti, L. Bonati, S. D’Oro, and T. Melodia, “SkyCell: A proto-typing platform for 5G aerial base stations, ” in 2020 IEEE 21st International Symposium on” A World of Wireless, Mobile and Multimedia Networks” (WoWMoM) . IEEE, 2020, pp. 329–334.

[6] H. Wang, H. Zhao, W. Wu, J. Xiong, D. Ma, and J. Wei, “Deployment algorithms of flying base stations: 5G and beyond with UAVs, ” IEEE Internet of Things Journal, vol. 6, no. 6, pp. 10009–10027, 2019.

[7] E. Kalantari, M. Z. Shakir, H. Yanikomeroglu, and A. Yongacoglu, “Backhaul-aware robust 3D drone placement in 5G+ wireless networks, ” in 2017 IEEE international conference on communications workshops (ICC workshops) . IEEE, 2017, pp. 109–114.

[8] C.T. Cicek, H. Gultekin, B. Tavli, and H. Yanikomeroglu, “Backhaul-aware optimization of UAV base station location and bandwidth allocation for profit maximization, ” IEEE Access, vol. 8, pp. 154 573–154 588, 2020.

[9] N. Tafintsev, D. Moltchanov, M. Gerasimenko, M. Gapeyenko, J. Zhu, S. -p. Yeh, N. Himayat, S. Andreev, Y. Koucheryavy, and M. Valkama, “Aerial access and backhaul in mmWave B5G systems: Performance dynamics and optimization, ” IEEE Communications Magazine, vol. 58, no. 2, pp. 93–99, 2020.

[10] C. Madapatha, B. Makki, C. Fang, O. Teyeb, E. Dahlman, M. -S. Alouini, and T. Svensson, “On integrated access and backhaul networks: Current status and potentials, ” IEEE Open Journal of the Communications Society, vol. 1, pp. 1374–1389, 2020.

[11] 3GPP, “Study on enhancement for data collection for NR and ENDC, ” 3rd Generation Partnership Project (3GPP) , Technical Rreport (TR) 37.817, 09 2021, version 0.3.0. [Online] . Available: https: //www. 3gpp. org/ftp/Specs/archive/37 series/37.817/37817-030. zip

[12] V. Mnih, K. Kavukcuoglu, D. Silver, A.A. Rusu, J. Veness, M. G. Bellemare, A. Graves, M. Riedmiller, A.K. Fidjeland, G. Ostrovski et al., “Human-level control through deep reinforcement learning, ” nature, vol. 518, no. 7540, pp. 529–533, 2015.

Claims

A computer implemented method for deploying at least one movable base station to serve at least one terminal device in a communication network, wherein the at least one terminal device is served either by a network node or served through the at least one movable base station which has a wireless backhaul link communicating with the network node functioning as a donor base station, the method comprising:

collecting (S102) , by a data collection module, data about measurements and/or performance metrics relating to the at least one terminal device to be served by at least one movable base station;

determining (S104) , by a model inference module, configuration for deploying the at least one movable base station, based on at least part of the collected data, wherein the determined configuration optimizes at least one of the performances metrics at the at least one terminal device, and by using the determined configuration, the at least one of the performances metrics is better when the at least one terminal device is served by the movable base station comparing to when the at least one terminal device is served by the network node; and

actuating (S106) , by an actor module, the at least one movable base station, based on at least the determined configuration.
The method according to claim 1,

wherein the data collection module is arranged at network side, and/or

wherein the data collection module is arranged near a source of the data.
The method according to any of claims 1 to 2,

wherein the data collection module is further configured to receive and apply feedback from the model inference module, and/or the actor module, and/or a central server;

wherein the feedback includes deployment strategy and/or suggested configuration based on algorithm prediction, and/or a global learning model; and

wherein the central server is located at the donor base station or a cloud.
The method according to claim 3,

wherein the deployment strategy and/or suggested configuration includes access antenna configuration, backhaul antenna configuration, backhaul routing path configuration, transmit power, 3-D location, and/or rotation/orientation of the at least one movable base station to serve the at least one terminal device.
The method according to any of claims 1 to 4,

wherein the collecting data is triggered by the donor base station for the at least one movable base station after the at least one movable base station completed a network integration procedure; or

wherein the collecting data is triggered after detecting a mobility event of the at least one movable base station; or

wherein the collecting data is triggered by the at least one movable base station, via a broadcasting message and/or a unicasting message and/or a multicasting message.
The method according to any of claims 1 to 5, wherein the collected data comprises at least one of:

load situation and/or resource utilization of the communication network;

geographic information of area to be served;

information about antenna tilting, and/or transmit power of a macro base station supporting or close to the at least one movable base station;

applied configuration for the at least one movable base station, including electrical/mechanical antenna tilting, rotation, 3D location, transmit power;

performance metrics relating to the applied configuration for the at least one movable base station, including statistics of the throughput, SINR, and drop rate of all connected users or a specific group of connected users for both DL and UL;

link quality for a backhaul relating to the at least one movable base station;

identity or location of the donor base station, number of wireless hops; and/or

user information including labels to distinguish different types of terminal devices or services, statistics about proportion of the different types of terminal devices or services served by the at least one movable base station, mobility information of the at least one terminal device.
The method according to any of claims 1 to 6,

wherein the collected data is divided into two sub-sets as training data and inference data;

wherein the training data is inputted to a model training module; and

wherein the inference data is inputted to the model inference module.
The method according to any of claims 1 to 7, further comprising:

training and updating (S103) a model used by the model inference module, by the model training module, based on at least the training data, and/or feedback from the model inference module.
The method according to claim 8,

wherein the model used by the model inference module is trained via an artificial intelligence/machine learning algorithm.
The method according to any of claim 8,

wherein the model inference module determines the configuration, by inputting a part of the collected data to the model and obtaining an output from the model; and/or

wherein the model inference module outputs the configuration to the model training module as feedback.
The method according to any of claims 1 to 10,

wherein the data collection module, the model inference module, and the actor module are integrated in a movable base station of the at least one movable base station, or in an edge-cloud, or the donor base station for supporting the at least one movable base station; or

wherein the data collection module, the model inference module, and the actor module are distributed in more than one base station, including movable base station and/or static base station.
The method according to any of claims 1 to 11,

wherein a target movable base station in the at least one movable base station is connected to the donor base station via single-hop wireless backhauling;

wherein the target movable base station is operative for:

collecting the data, via data reports from the at least one terminal device, and/or the donor base station, and/or a set of other selected base stations;

training a model used by the model inference module, based on at least part of the collected data;

generating the configuration for deploying the target movable base station, based on at least part of the collected data;

actuating the target movable base station, based on at least the configuration; and

feedbacking the configuration to the donor base station, and/or the set of other selected base stations.
The method according to claim 12,

wherein the data reports are triggered by the donor base station, or the target movable base station.
The method according to any of claims 1 to 11,

wherein a target movable base station in the at least one movable base station is connected to the donor base station via single-hop wireless backhauling;

wherein the donor base station is operative for:

collecting the data, via data reports from the at least one terminal device, and/or the target movable base station, and/or a set of other selected base stations;

training a model used by the model inference module, based on at least part of the collected data;

generating the configuration for deploying the target movable base station, based on at least part of the collected data; and

feedbacking the configuration to the target movable base station, and/or the set of other selected base stations;

wherein the target movable base station is operative for:

collecting and transmitting data to the donor base station; and

taking action, based on the configuration.
The method according to claim 14,

wherein the data reports are triggered by the donor base station, or the target movable base station.
The method according to any of claims 1 to 11,

wherein a target movable base station in the at least one movable base station is connected to the donor base station via single-hop wireless backhauling;

wherein the donor base station is operative for:

collecting the data, via data reports from the at least one terminal device, and/or the target movable base station, and/or a set of other selected base stations;

training a model used by the model inference module, based on at least part of the collected data;

transmitting, to the target movable base station, at least part of the collected data, and/or update for the model;

cooperating with the target movable base station for generating the configuration for deploying the target movable base station, based on at least part of the collected data; and

feedbacking the configuration to the target movable base station, and/or the set of other selected base stations;

wherein the target movable base station is operative for:

collecting and transmitting data to the donor base station;

receiving, from the donor base station, at least part of the collected data, and/or update for the model;

cooperating with the donor base station for generating the configuration for deploying the target movable base station, based on at least part of the collected data;

taking action, based on the configuration; and

feedbacking the configuration to the donor base station, and/or the set of other selected base stations.
The method according to claim 16,

wherein the data reports are triggered by the donor base station, or the target movable base station.
The method according to any of claims 1 to 11,

wherein a target movable base station in the at least one movable base station is connected to the donor base station via multi-hop wireless backhauling;

wherein the multi-hop wireless backhauling comprises at least one intermediate movable base station;

wherein the target movable base station is operative for:

collecting the data, via data reports from the at least one terminal device, and/or at least one intermediate movable base station, and/or the donor base station, and/or a set of other selected base stations;

training a model used by the model inference module, based on at least part of the collected data;

cooperating with the at least one intermediate movable base station for generating the configuration for deploying the target movable base station, based on at least part of the collected data and feedback from the at least one intermediate movable base station;

taking action, based on the configuration; and

feedbacking the configuration to the at least one intermediate movable base station, and/or the donor base station, and/or a set of other selected base stations;

wherein the at least one intermediate movable base station is operative for:

cooperating with the target movable base station, and/or other intermediate movable base stations, for generating another configuration for deploying the at least one intermediate movable base station, based on at least part of the collected data and feedback from the target movable base station;

feedbacking another configuration to the donor base station, and/or the set of other selected base stations.
The method according to claim 18,

wherein the data reports are triggered by the donor base station, or the target movable base station.
The method according to any of claims 12 to 19, wherein the donor base station or the target movable base station is further operative for:

triggering further data reports for updating the model used by the model inference module.
The method according to any of claims 12 to 20, wherein the donor base station is further operative for:

aggregating feedback from each of the at least one movable base station;

updating a model hosted in each of the at least one movable base station.
The method according to claim 21,

wherein updating the model is triggered by the donor base station, or the at least one movable base station.
The method according to any of claims 1 to 22,

wherein the at least one terminal device comprises at least one mission critical users; and/or

wherein the at least one movable base station comprises at least one unmanned aerial vehicle base station, UAV-BS.
An apparatus (10) for deploying at least one movable base station to serve at least one terminal device in a communication network, wherein the at least one terminal device is served either by a network node or served through the at least one movable base station which has a wireless backhaul link communicating with the network node functioning as a donor base station, the apparatus comprising:

at least one processor (101) ; and

at least one memory (102) , the at least one memory (102) containing instructions executable by the at least one processor, whereby the apparatus (10) is operative for:

collecting, by a data collection module, data about measurements and/or performance metrics relating to the at least one terminal device to be served by at least one movable base station;

determining, by a model inference module, configuration for deploying the at least one movable base station, based on at least part of the collected data, wherein the determined configuration optimizes at least one of the performances metrics at the at least one terminal device, and by using the determined configuration, the at least one of the performances metrics is better when the at least one terminal device is served by the movable base station comparing to when the at least one terminal device is served by the network node; and;

actuating, by an actor module, the at least one movable base station, based on at least the determined configuration.
The apparatus (10) according to claim 24, wherein the apparatus (10) is further operative to perform the method according to any of claims 2 to 23.
A computer-readable storage medium (700) storing instructions (701) which when executed by at least one processor, cause the at least one processor to perform the method according to any one of claims 1 to 23.