WO2025065266A1

WO2025065266A1 - Energy consumption prediction for wireless communication

Info

Publication number: WO2025065266A1
Application number: PCT/CN2023/121697
Authority: WO
Inventors: Zhuang Liu; Yuxuan TAN; Jiajun Chen; Man ZHANG; Dapeng Li; Yin Gao
Original assignee: ZTE Corp
Current assignee: ZTE Corp
Priority date: 2023-09-26
Filing date: 2023-09-26
Publication date: 2025-04-03
Anticipated expiration: 2026-03-26

Abstract

In wireless communication, a measured energy consumption (EC) information for a user equipment (UE) can be used for predicting the EC information for the UE. With the application of Artificial Intelligence/Machine Learning (AI/ML), a network may be able to predict the energy consumption of nodes or UEs in advance. This predicted energy consumption can be utilized for energy-saving strategies. This may improve the quality of service (QoS) provided to UEs and avoid interruptions to UE services.

Description

ENERGY CONSUMPTION PREDICTION FOR WIRELESS COMMUNICATION

TECHNICAL FIELD

This document is directed generally to wireless communications. More specifically, in a mobile device communications system, there may be improved energy consumption by predicting energy usage.

BACKGROUND

Wireless communication technologies are moving the world toward an increasingly connected and networked society. Wireless communications rely on efficient network resource management and allocation between user mobile stations and wireless access network nodes (including but not limited to wireless base stations) . A new generation network is expected to provide high speed, low latency and ultra-reliable communication capabilities and fulfil the requirements from different industries and users. User mobile stations or user equipment (UE) are becoming more complex and the amount of data communicated continually increases. In order to improve communications and meet reliability requirements for the vertical industry as well as support the new generation network service, communication improvements should be made.

5G New Radio (NR) may be designed to enable denser network deployments. This density of networks has led to higher energy usage. In a Radio Access Network (RAN) , energy may be predominantly consumed by basestations. Energy consumption costs may be a significant part of the operational expenses (OPEX) for 5G telecommunication operators. With the anticipated deployment of more basestations with massive Multiple-Input Multiple-Output (MIMO) , energy efficiency (EE) in NR becomes even more urgent and challenging.

SUMMARY

This document relates to methods, systems, and devices for wireless communications that can improve energy usage. Energy saving techniques must still allow the mobile network to fulfill service requirements, including reliable coverage where users want to access services, enough capacity to serve traffic demand, and a service quality that satisfies users' Quality of Service (QoS) expectations. Embodiments include used measured energy consumption (EC) information for a user equipment (UE) and predicting the EC information for the UE based on the measured EC information. With the application of Artificial Intelligence/Machine Learning (AI/ML) , a network may be able to predict the energy consumption of nodes or UEs in advance. This predicted energy consumption can be utilized for energy-saving strategies. This may improve the quality of service (QoS) provided to UEs and avoid interruptions to UE services.

In one embodiment, a wireless communication method includes receiving measured energy consumption (EC) information for a user equipment (UE) ; and predicting the EC information for the UE based on the measured EC information.

In one embodiment, a wireless communication method includes providing additional user equipment (UE) information; and receiving a predicted energy consumption (EC) information for the UE based on the additional UE information.

In one embodiment, a wireless communication method includes providing additional traffic information about a source node; and receiving a predicted energy consumption (EC) information for the source node based on the additional traffic information. In one embodiment, a wireless communications apparatus comprises a processor and a memory, and the processor is configured to read code from the memory and implement any of the embodiments discussed above.

In one embodiment, a computer program product comprises a computer-readable program medium code stored thereupon, the code, when executed by a processor, causes the processor to implement any of the embodiments discussed above.

In some embodiments, there is a wireless communications apparatus comprising a processor and a memory, wherein the processor is configured to read code from the memory and implement any methods recited in any of the embodiments. In some embodiments, a computer program product comprising a computer-readable program medium code stored thereupon, the code, when executed by a processor, causing the processor to implement any method recited in any of the embodiments. The above and other aspects and their implementations are described in greater detail in the drawings, the descriptions, and the claims.

BRIEF DESCRIPTION OF THE DRAWINGS

FIG. 1 shows an example basestation.

FIG. 2 shows an example random access (RA) messaging environment.

FIG. 3 shows a network architecture of a basestation Central Unit (CU) and basestation Distributed Unit (DU) .

FIG. 4 shows an embodiment of a wireless network system architecture.

FIG. 5 shows an example artificial intelligence (AI) model or processing method.

FIG. 6 shows communications with a source node predicting energy consumption.

FIG. 7 shows communications with a target node predicting energy consumption.

FIG. 8 shows communications a node associated energy consumption prediction.

FIG. 9 shows communications for receiving an energy consumption prediction.

DETAILED DESCRIPTION

The present disclosure will now be described in detail hereinafter with reference to the accompanied drawings, which form a part of the present disclosure, and which show, by way of illustration, specific examples of embodiments. Please note that the present disclosure may, however, be embodied in a variety of different forms and, therefore, the covered or claimed subject matter is intended to be construed as not being limited to any of the embodiments to be set forth below.

Throughout the specification and claims, terms may have nuanced meanings suggested or implied in context beyond an explicitly stated meaning. Likewise, the phrase “in one embodiment” or “in some embodiments” as used herein does not necessarily refer to the same embodiment and the phrase “in another embodiment” or “in other embodiments” as used herein does not necessarily refer to a different embodiment. The phrase “in one implementation” or “in some implementations” as used herein does not necessarily refer to the same implementation and the phrase “in another implementation” or “in other implementations” as used herein does not necessarily refer to a different implementation. It is intended, for example, that claimed subject matter includes combinations of exemplary embodiments or implementations in whole or in part.

In general, terminology may be understood at least in part from usage in context. For example, terms, such as “and” , “or” , or “and/or, ” as used herein may include a variety of meanings that may depend at least in part upon the context in which such terms are used. Typically, “or” if used to associate a list, such as A, B or C, is intended to mean A, B, and C, here used in the inclusive sense, as well as A, B or C, here used in the exclusive sense. In addition, the term “one or more” or “at least one” as used herein, depending at least in part upon context, may be used to describe any feature, structure, or characteristic in a singular sense or may be used to describe combinations of features, structures or characteristics in a plural sense. Similarly, terms, such as “a” , “an” , or “the” , again, may be understood to convey a singular usage or to convey a plural usage, depending at least in part upon context. In addition, the term “based on” or “determined by” may be understood as not necessarily intended to convey an exclusive set of factors and may, instead, allow for existence of additional factors not necessarily expressly described, again, depending at least in part on context.

The Energy Saving (ES) state may be a state in which some functions of a cell or network are powered down. To achieve an energy-efficient or green RAN, energy-saving techniques such as switching off cells with no or very light load during off-peak conditions may be used to reduce network energy consumption. Instead of switching off the entire cell, an enhanced ES technique may be implemented by shutting down some cell equipment, including but not limited to power amplifiers, transceivers, and other network elements. This may allow the cell to enter into an energy-saving state while still providing a certain cell capacity. By shutting down more or less equipment, the cell can enter into another energy-saving state with different cell capacity. Energy saving must still allow the mobile network to fulfill service requirements. It must provide reliable coverage where users want to access services, enough capacity to serve traffic demand, and a service quality that satisfies users' Quality of Service (QoS) expectations. When a 5G RAN or basestation supports different energy states and dynamically changes the energy state of cells for network energy saving, the network coverage, capacity, and QoS of services provided to users may be affected. The energy-saving techniques/schemes described in the embodiments below intend to maintain user satisfaction without degrading QoS.

Energy consumption costs may be a significant part of the operational expenses (OPEX) for telecommunication operators. In order to ensure the "green" communications in a wireless network and decrease the network energy consumption, the network may be configured with a Network Energy Saving (NES) policy that is used by the network for network energy saving purposes (e.g., enforcing network energy efficiency, enforcing network energy consumption limitations, or ensuring the quality of services under some energy consumption limitation, etc. ) . An Energy Consumption (EC) rate may be the total amount of energy consumed of the specific composition of network resources used for providing services to the UE (i.e. at the “UE level” ) or at all UEs severed by the network node. The Network Energy Efficiency may be the ratio between the produced performance of service (e.g. data rate, data delay, etc. ) by the network. The energy consumed by the network resources to produce the service for the UE level or the node level may be: the network data energy efficiency = (network data volume /network energy consumption) [bit/J] or [Mbit/kWh] . Enforcing a network energy consumption limitation may include a limitation/target/minimum of the network energy consumption rate for the UE or for the network node, or it may be a limitation of an accumulated amount of energy consumed for the UE or for the network. Enforcing the network energy efficiency may include the enforcement of the target/minimum of the network energy efficiency for the UE or for the network node.

With the application of Artificial Intelligence/Machine Learning (AI/ML) , a network may be able to predict the energy consumption of nodes or UEs in advance. This predicted energy consumption can be utilized for energy-saving strategies. This may improve the quality of service (QoS) provided to UEs and avoid interruptions to UE services.

Radio resource control ( “RRC” ) is a protocol layer between UE and the basestation at the IP level (Network Layer) . There may be various Radio Resource Control (RRC) states, such as RRC connected (RRC_CONNECTED) , RRC inactive (RRC_INACTIVE) , and RRC idle (RRC_IDLE) state. RRC messages are transported via the Packet Data Convergence Protocol ( “PDCP” ) . As described, UE can transmit data through a Random Access Channel ( “RACH” ) protocol scheme or a Configured Grant ( “CG” ) scheme. CG may be used to reduce the waste of periodically allocated resources by enabling multiple devices to share periodic resources. The basestation or node may assign CG resources to eliminate packet transmission delay and to increase a utilization ratio of allocated periodic radio resources. The CG scheme is merely one example of a protocol scheme for communications and other examples, including but not limited to RACH, are possible. The wireless communications described herein may be through radio access. FIGs. 1 to 4 show example radio access network ( “RAN” ) nodes (e.g. basestations) and user equipment and messaging environments, which may be applicable the energy saving prediction described below.

FIG. 1 shows an example basestation 102. The basestation may also be referred to as a wireless network node and may be the network nodes (e.g. master node ( “MN” ) , secondary node ( “SN” ) , and the source/target nodes) shown in FIGs. 6 to 9. The basestation 102 may be further identified to as a nodeB (NB, e.g., an eNB or gNB) in a mobile telecommunications context. The example basestation may include radio Tx/Rx circuitry 113 to receive and transmit with user equipment (UEs) 104. The basestation may also include network interface circuitry 116 to couple the basestation to the core network 110, e.g., optical or wireline interconnects, Ethernet, and/or other data transmission mediums/protocols.

The basestation may also include system circuitry 122. System circuitry 122 may include processor (s) 124 and/or memory 126. Memory 126 may include operations 128 and control parameters 130. Operations 128 may include instructions for execution on one or more of the processors 124 to support the functioning the basestation. For example, the operations may handle random access transmission requests from multiple UEs. The control parameters 130 may include parameters or support execution of the operations 128. For example, control parameters may include network protocol settings, random access messaging format rules, bandwidth parameters, radio frequency mapping assignments, and/or other parameters.

FIG. 2 shows an example random access messaging environment 200. In the random access messaging environment a UE 104 may communicate with a basestation 102 over a random access channel 252. In this example, the UE 104 supports one or more Subscriber Identity Modules (SIMs) , such as the SIM1 202. Electrical and physical interface 206 connects SIM1 202 to the rest of the user equipment hardware, for example, through the system bus 210.

The mobile device 200 includes communication interfaces 212, system logic 214, and a user interface 218. The system logic 214 may include any combination of hardware, software, firmware, or other logic. The system logic 214 may be implemented, for example, with one or more systems on a chip (SoC) , application specific integrated circuits (ASIC) , discrete analog and digital circuits, and other circuitry. The system logic 214 is part of the implementation of any desired functionality in the UE 104. In that regard, the system logic 214 may include logic that facilitates, as examples, decoding and playing music and video, e.g., MP3, MP4, MPEG, AVI, FLAC, AC3, or WAV decoding and playback; running applications; accepting user inputs; saving and retrieving application data; establishing, maintaining, and terminating cellular phone calls or data connections for, as one example, Internet connectivity; establishing, maintaining, and terminating wireless network connections, Bluetooth connections, or other connections; and displaying relevant information on the user interface 218. The user interface 218 and the inputs 228 may include a graphical user interface, touch sensitive display, haptic feedback or other haptic output, voice or facial recognition inputs, buttons, switches, speakers and other user interface elements. Additional examples of the inputs 228 include microphones, video and still image cameras, temperature sensors, vibration sensors, rotation and orientation sensors, headset and microphone input /output jacks, Universal Serial Bus (USB) connectors, memory card slots, radiation sensors (e.g., IR sensors) , and other types of inputs.

The system logic 214 may include one or more processors 216 and memories 220. The memory 220 stores, for example, control instructions 222 that the processor 216 executes to carry out desired functionality for the UE 104. The control parameters 224 provide and specify configuration and operating options for the control instructions 222. The memory 220 may also store any BT, WiFi, 3G, 4G, 5G or other data 226 that the UE 104 will send, or has received, through the communication interfaces 212. In various implementations, the system power may be supplied by a power storage device, such as a battery 282.

In the communication interfaces 212, Radio Frequency (RF) transmit (Tx) and receive (Rx) circuitry 230 handles transmission and reception of signals through one or more antennas 232. The communication interface 212 may include one or more transceivers. The transceivers may be wireless transceivers that include modulation /demodulation circuitry, digital to analog converters (DACs) , shaping tables, analog to digital converters (ADCs) , filters, waveform shapers, filters, pre-amplifiers, power amplifiers and/or other logic for transmitting and receiving through one or more antennas, or (for some devices) through a physical (e.g., wireline) medium.

The transmitted and received signals may adhere to any of a diverse array of formats, protocols, modulations (e.g., QPSK, 16-QAM, 64-QAM, or 256-QAM) , frequency channels, bit rates, and encodings. As one specific example, the communication interfaces 212 may include transceivers that support transmission and reception under the 2G, 3G, BT, WiFi, Universal Mobile Telecommunications System (UMTS) , High Speed Packet Access (HSPA) +, and 4G /Long Term Evolution (LTE) standards. The techniques described below, however, are applicable to other wireless communications technologies whether arising from the 3rd Generation Partnership Project (3GPP) , GSM Association, 3GPP2, IEEE, or other partnerships or standards bodies.

Multiple RAN nodes of the same or different radio access technology ( “RAT” ) (e.g. eNB, gNB) can be deployed in the same or different frequency carriers in certain geographic areas, and they can inter-work with each other via a dual connectivity operation to provide joint communication services for the same target UE (s) . The multi-RAT dual connectivity ( “MR-DC” ) architecture may have non-co-located master node ( “MN” ) and secondary node ( “SN” ) . Access Mobility Function ( “AMF” ) and Session Management Function ( “SMF” ) may the control plane entities and User Plane Function ( “UPF” ) is the user plane entity in new radio ( “NR” ) or 5GC. The signaling connection between AMF/SMF and the master node ( “MN” ) may be a Next Generation-Control Plane ( “NG-C” ) /MN interface. The signaling connection between MN and SN may an Xn-Control Plane ( “Xn-C” ) interface. The signaling connection between MN and UE is a Uu-Control Plane ( “Uu-C” ) RRC interface. All these connections manage the configuration and operation of MR-DC. The user plane connection between User Plane Function ( “UPF” ) and MN may be NG-U (MN) interface instance.

FIG. 3 shows a network architecture of a basestation Central Unit (CU) and basestation Distributed Unit (DU) . FIG. 3 illustrates basestations (labeled as “gNB” ) that communicate with an overall network (labeled ( “5GC” ) . Basestations can communicate with one another via a control plane interface ( “Xn-C” ) . One basestation is shown as have one CU that is connected to two DUs via an F1 interface. This is merely one example of an arrangement of a basestation. In some embodiments, there may be one or any number of DUs connected with a single CU.

The basestation can be divided into two physical entities named Centralized Unit ( “CU” ) and Distributed Unit ( “DU” ) . Generally, the CU may provide support for the higher layers of the protocol stack such as SDAP, PDCP and RRC while the DU provides support for the lower layers of the protocol stack such as RLC, MAC and Physical layer. The CU may include operations for a transfer of user data, mobility control, radio access network sharing, session management, etc., except those functions allocated exclusively to the DU. The DU (s) are logical node (s) with a subset of the basestation functions, and may be controlled by the CU.

The CU may be a logical node hosting RRC, SDAP and PDCP protocols of the basestation or RRC and PDCP protocols of the basestation that controls the operation of one or more DUs. The DU may be a logical node hosting RLC, MAC and PHY layers of the basestation, and its operation may be at least partly controlled by the CU. A single DU may support one or multiple cells. However, each cell is only supported by a single DU. Each basestation may support many cells. As described in the embodiments herein, the cell mobility between cells may be from different CUs or DUs or may be internal to the CU and/or the DU. Further, the mobility may be from a source node to a target node. As described the source/target nodes may be the CU/DU.

FIG. 4 shows an embodiment of a wireless network system architecture. This architecture is merely one example and there may be more or fewer components for implementing the embodiments described herein. The interconnections or communications between components are identified as N1, N2, N4, N6, N7, N8, N10, and N11, which may be referred to in the description or by other Figures. FIG. 2 illustrated an example user equipment ( “UE” ) 104. UE 402 is a device accessing a wireless network (e.g. 5GS) and obtaining service via a NG-RAN node or basestation 404. The UE 402 interacts with an Access and Mobility Control Function ( “AMF” ) 406 of the core network via NAS signaling. FIG. 1 illustrates an example basestation or NG-RAN 102. The NG-RAN node 404 is responsible for the air interface resource scheduling and air interface connection management of the network to which the UE accesses. The AMF 406 includes the following functionalities: Registration management, Connection management, Reachability management and Mobility Management. The AMF 406 also perform the access authentication and access authorization. The AMF 406 is the NAS security termination and relay the session management NAS between the UE 402 and the SMF 408, etc.

The SMF 408 includes the following functionalities: Session Management e.g. Session establishment, modify and release, UE IP address allocation & management (including optional Authorization) , Selection and control of uplink function, downlink data notification, etc. The user plane function ( “UPF” ) 410 includes the following functionalities: Anchor point for Intra-/Inter-RAT mobility, Packet routing & forwarding, Traffic usage reporting, QoS handling for user plane, downlink packet buffering and downlink data notification triggering, etc. The Unified Data Management ( “UDM” ) 412 manages the subscription profile for the UEs. The subscription includes the data used for mobility management (e.g. restricted area) , session management (e.g. QoS profile) . The subscription data also includes slice selection parameters, which are used for AMF 406 to select a proper SMF 408. The AMF 406 and SMF 408 get the subscription from the UDM 412. The subscription data may be stored in a Unified Data Repository with the UDM 412, which uses such data upon reception of request from AMF 406 or SMF 408. The Policy Control Function ( “PCF” ) 414 includes the following functionality: supporting unified policy framework to govern network behavior, providing policy rules to control plane function (s) to enforce the policy rule, and implementing a front end to access subscription information relevant for policy decisions in the User Data Repository. The Network Exposure Function ( “NEF” ) 416 is deployed optionally for exchanging information with an external third party. In one embodiment, an Application Function ( “AF” ) 416 may store the application information in the Unified Data Repository via NEF. The UPF 410 communicates with the data network 418.

Access Mobility Function ( “AMF” ) and Session Management Function ( “SMF” ) are the control plane entities and User Plane Function ( “UPF” ) is the user plane entity in new radio ( “NR” ) or 5GC. The signaling connection between AMF/SMF and MN may be a Next Generation-Control Plane ( “NG-C” ) /MN interface. The signaling connection between MN and SN may be an Xn-Control Plane ( “Xn-C” ) interface. The signaling connection between MN and UE may be a Uu-Control Plane ( “Uu-C” ) RRC interface.

FIG. 5 shows an example artificial intelligence (AI) processing method. The processing method and/or processing method setting may include AI or Machine Learning (ML) models/algorithms. This processing method may be used to predict energy consumption at the UE. In embodiments described below, the wireless communication system of FIGs. 1 to 4 may be improved with increased energy efficiency by using the predicted energy usage. The Artificial Intelligence/Machine Learning (AI/ML) processing method in FIG. 5 is a data driven algorithm that applies AI/ML techniques to generate a set of outputs based on a set of inputs. As shown, there may be a processing method input, which includes the data fed into the processing method. There may be a processing method output, which includes the output of the processing method. The processing method may include an algorithm/model to derive the relationship between the processing method input and processing method output.

Artificial Intelligence/Machine Learning (AI/ML) can be used to improve the energy efficiency of wireless communication systems. As described, the processing method with AI/ML models deployed at the UE can be used to predict energy usage. In the following embodiments, the processing method can also include (or be referred to as) a functionality, an AI/ML model, or a feature. It may include when a UE is capable of doing a specific functionality, processing method, an AI/ML model, or a feature. The functionality, processing method, or a feature may be enabled by one or multiple AI/ML models. In some embodiments, the processing method may only apply for certain environments and this may be referred to generalization, where good generalization suggests that the processing method can be used in more environments or configurations.

FIG. 6 shows communications with a source node predicting energy consumption. In this embodiment, UE associated network energy consumption (EC) is predicted by the source node. As described throughout, the energy consumption (EC) may be reflected in information (i.e. EC info) that is utilized for network energy saving. The energy saving may include enforcing a network energy efficiency, enforcing a network energy consumption limitation, or ensuring the quality of services (QoS) under an energy consumption limitation.

In some embodiments, the source node may include a Core Network (CN) and the target node is a basestation (e.g. gNB) . In another embodiment, the source node is a basestation (gNB) and the target node is another basestation. In another embodiment, the source node is a basestation Centralized Unit (CU) and the target node is a basestation Distributed Unit (DU) . In another embodiment, the source node is a basestation Control Plane of the Centralized Unit (CU-CP, such as a gNB-CU-CP) , and the target node is a basestation User Plane of the Centralized Unit (CU-UP, such as a gNB-CU-UP) .

The source node may be preparing to handover one or more UEs or to request/modify resources to establish/modify quality of service (QoS) flows for the one or more UEs at the target node. In block 602, the energy consumption (EC) information at the target node is predicted. The collected historical measured EC information of UEs may be used for improved EC. This may include enforcing network energy efficiency, a network energy consumption limitation, or ensuring the quality of user services under an EC limitation. The source node may utilized AI/ML (e.g. the processing method enabled by the AI/ML model as in FIG. 5) to predict the EC information of prepared UEs and/or the QoS performance (e.g., packet loss, data rate, transmission delay, jitters, etc. ) for the QoS flows to be set up from prepared UEs at the target node. There may be a determination as to whether to accept or reject some QoS flows setup or a UE handover based on the predicted information as in block 604. This may consider a configured policy of network energy saving, such as the network energy consumption limitation of the UE or UE's service and/or whether the QoS performance requirement can be met under some network energy consumption limitation for UE.

Before requesting the target node allocate resources for the QoS flow (s) of one or more prepared UEs, the source node sends the UE EC information request message to the target node in block 606. This request message may initiate the network energy consumption report/measurement procedure for prepared UEs at the target node, including a source node allocated EC request identifier to identify the initiated UE EC reporting instance.

If the source Node decides to handover some UEs, or to establish some QoS flows for some UEs at the target node, the source node sends the UE associated message to the target node to request allocating resource for the UE in block 608. The request may include the previous source node allocated EC request identifier in the message to request the previously initiated UE EC report of the concerned UE. For example, if the source node is the CN, the source node may send a PDU session setup/modification request message, an initial UE context setup request message, or a Handover Request message, via the NG interface. Alternatively, if the source node is the basestation, the source node may send a Handover Request message, a SN addition request message, or a SN modification request message via the Xn interface. Alternatively, if the source node is the basestation-CU, the source node may send a UE Context setup request message, or a UE Context modification request message, via the F1 interface. Alternatively, if the source node is the basestation-CU-CP, the source node may send a bearer context setup request message, or a bearer context modification request message via E1 interface.

After the QoS flows of UE (s) have been successfully established or UE (s) has/have been through a successful handover at the target node, there may be a UE EC report in block 610. If the source node allocated EC request ID is included in the previous request message associated with the concerned UE for resource allocation at the target node, then the target Node reports the measured EC information of the corresponding concerned UEs to the source node within the UE EC report during the measured period. The measured UE EC info may include a source node allocated EC request ID to identify the previously initiated UE EC measurement report instance, or a list of UE identifiers. For each indicated UE, it may include at least one of: an energy consumption rate, energy consumption, energy efficiency of the network resources used for the specific UE, specific slice of UE, specific QoS flow of UE, or a specific PDU session of UE. It may further include a QoS measurement (e.g. packet loss, data rate, transmission delay, jitters, etc. ) for the specific service (e.g. QoS flow) of the UE.

The target node uses the received UE EC report as the feedback data for AI/ML model training/optimizing as in block 612. This report may be used as the input data for the AM/ML prediction of EC for subsequent iterations. This may be a model input as shown in FIG. 5 to improve the model for the future predictions.

FIG. 7 shows communications with a target node predicting energy consumption. The UE associated network energy consumption is predicted by the target node. As described throughout, the energy consumption (EC) may be reflected in information (i.e. EC info) that is utilized for network energy saving. The energy saving may include enforcing a network energy efficiency, enforcing a network energy consumption limitation, or ensuring the quality of services (QoS) under an energy consumption limitation.

In block 702, the source node is preparing to provide services for one or more UEs via the target node, or to handover one or more UEs to the target node. This may include the services discussed herein that are necessary for the UE to utilize the target node.

In block 704, the source node sends the energy consumption (EC) request message to the target node to request EC information of the prepared UEs, including the additional UE information in the message. The additional UE information may be associated with one or more UEs, and include at least one of the following:

● a list of UE identifiers;

● for each indicated UE, the QoS flow information of the additional services (e.g. Qos flows prepared to be set up at the target node) of the UE, where the QoS flow information including the QoS identifier and QoS parameters;

● the target cell identifier for each indicated UE; or

● the slice identifier (s) used for the UE for each indicated UE.

In block 706, after receiving the request message, the target node uses AI/ML (see e.g. FIG. 5) to predict the EC information for the additional services of the prepared UEs indicated by the request message. In block 708, the target node sends the predicted UE EC information within the UE EC report to the source node. The predicted UE EC information may include at least one of the following:

● a list of UE identifiers; and/or

● for each indicated UE including at least one of: the predicted energy consumption rate, predicted energy consumption, and/or the predicted energy efficiency of the predicted network resources used for the specific UE, the specific slice of UE, specific PDU session of UE, or the specific QoS flow of UE. It may include a predicted QoS measurement (e.g. packet loss, data rate, transmission delay, jitters, etc. ) for the specific service (QoS flow) of the UE.

Based on the received predicted UE EC information, and in order to enforce network energy efficiency, a network energy consumption limitation, or to ensure the quality of user services under some energy consumption limitation, the source node determines whether to accept or reject some QoS flows setup as in block 710. In other embodiments, the source node determines whether to accept/reject a UE handover, while considering the configured policy of network energy saving (e.g., the network energy consumption limitation of the UE or UE's service and/or whether the QoS performance requirement can be met under some network energy consumption limitation for UE) .

FIG. 8 shows communications a node associated energy consumption prediction. In this embodiment, the source node requests the predicted node associated EC information from the target node or predicts the node associated EC information, and utilizes the predicted EC information for network energy saving. The energy saving may include enforcing a network energy efficiency, enforcing a network energy consumption limitation, or ensuring the quality of services (QoS) under an energy consumption limitation.

In block 802, the source node is preparing to handover some UEs, or to prepare to request resources to establish some QoS flows of some UEs at the target node. Based on the collected historical EC information of the target node (e.g., collecting in block 806) , in order to enforce network energy efficiency, a network energy consumption limitation, or to ensure the quality of user services under some energy consumption limitation, the source node uses AI/ML to predict the EC information of the target node considering the additional traffic load of the QoS flows to be set up of prepared UEs. The QoS performance (e.g. packet loss, data rate, transmission delay, jitters, etc. ) for the QoS flows to be set up of prepared UEs at the target node or receives the predicted node EC information for the additional traffic load from the target node (such as in the receiving in block 606) . A determination is made as to whether to accept or reject some QoS flows setup or UE handover based on the predicted information, while considering the configured policy of network energy saving (e.g., the network energy consumption limitation of the target node/cell and/or whether the QoS performance requirement can be met under some network energy consumption limitation for the target node/cell) .

Before requesting the target node to allocate resource for the QoS flow (s) of one or more prepared (additional) UEs, the source node sends the node energy consumption (EC) information request message to the target node to initiate the network energy consumption report/measurement procedure at the target Node in block 804. The source node may be optional including the additional traffic information for prepared UEs in the message. The additional traffic information is associated with the node and includes at least one of the following:

● the number of additional UEs of a specific cell, a specific slice, or the node;

● the number of additional RRC connection of a specific cell, a specific slice, or the node;

● the number of additional PRB needed for all additional QoS flows of a specific cell, a specific slice, or the node;

● the number of additional specific type of QoS flow (service) of a specific cell, a specific slice, or the node;

● the total additional traffic load (e.g., data rate) of all the additional services (Qos flows) of additional UEs severed by a specific cell, a specific slice, or the node; or

● the total additional traffic load (e.g., data rate) of the specific type of service (e.g. Qos flow) of additional UEs severed by a specific cell, a specific slice, or the node.

After receiving the node information request, if the additional load information is not present, the target node reports the measured node EC information within the node EC report to the source node in block 806. The target predicts the node EC information only considering the historical measured traffic information/pattern at the target node, and reports the corresponding predicted node EC information to the source node in block 806. Otherwise, the target may predict the node EC information considering the additional traffic information and report the corresponding predicted node EC information within the node EC report to the source node.

The measured node EC information may include at least one of the following: energy consumption rate, energy consumption, or energy efficiency, of the network resources used for the specific cell, specific slice, or the node. It may also include an average QoS measurement (e.g. packet loss, data rate, transmission delay, jitters, etc. ) for the specific service (QoS flow) of all UEs severed by a specific cell, a specific slice, or the node.

The predicted node EC information may consider both current traffic and additional traffic, may include the predicted delta/increased node EC information associated with the additional traffic, may consider the historical measured traffic information (i.e. without considering the indicated additional traffic) . Each type of predicted EC information includes at least one of the following: predicted delta energy consumption rate, predicted delta energy consumption, or predicted delta energy efficiency of the network resources used for the specific cell, specific slice, or the node. The predicted delta average QoS measurement (e.g. packet loss, data rate, transmission delay, jitters, etc. ) for the specific service (QoS flow) of all UEs severed by a specific cell, a specific slice, or the node.

The target node uses the received UE EC report as the feedback data for AI/ML model training/optimizing as in block 808. This report may be used as the input data for the AM/ML prediction of EC for subsequent iterations. This may be a model input as shown in FIG. 5 to improve the model for the future predictions.

FIG. 9 shows communications for receiving an energy consumption prediction. The communications in FIG. 9 may be similar to those in FIG. 8, except the predicted node energy consumption (EC) information is received from the target node rather than determined by the source node. In other words, in block 902 the predicted node EC information is received at the source node.

Based on the collected historical EC information of the target node (e.g., collecting in block 906) , in order to enforce network energy efficiency, a network energy consumption limitation, or to ensure the quality of user services under some energy consumption limitation, the source node uses AI/ML to predict the EC information of the target node considering the additional traffic load of the QoS flows to be set up of prepared UEs. The QoS performance (e.g. packet loss, data rate, transmission delay, jitters, etc. ) for the QoS flows to be set up of prepared UEs at the target node or receives the predicted node EC information for the additional traffic load from the target node (such as in the receiving in block 606) . A determination is made as to whether to accept or reject some QoS flows setup or UE handover based on the predicted information, while considering the configured policy of network energy saving (e.g., the network energy consumption limitation of the target node/cell and/or whether the QoS performance requirement can be met under some network energy consumption limitation for the target node/cell) .

Before requesting the target node to allocate resource for the QoS flow (s) of one or more prepared (additional) UEs, the source node sends the node energy consumption (EC) information request message to the target node to initiate the network energy consumption report/measurement procedure at the target Node in block 904. The source node may be optional including the additional traffic information for prepared UEs in the message. The additional traffic information is associated with the node and includes at least one of the following:

After receiving the node information request, if the additional load information is not present, the target node reports the measured node EC information within the node EC report to the source node in block 906. The target predicts the node EC information only considering the historical measured traffic information/pattern at the target node, and reports the corresponding predicted node EC information to the source node in block 906. Otherwise, the target may predict the node EC information considering the additional traffic information and report the corresponding predicted node EC information within the node EC report to the source node.

The target node uses the received UE EC report as the feedback data for AI/ML model training/optimizing as in block 908. This report may be used as the input data for the AM/ML prediction of EC for subsequent iterations. This may be a model input as shown in FIG. 5 to improve the model for the future predictions.

The system and process described above may be encoded in a signal bearing medium, a computer readable medium such as a memory, programmed within a device such as one or more integrated circuits, one or more processors or processed by a controller or a computer. That data may be analyzed in a computer system and used to generate a spectrum. If the methods are performed by software, the software may reside in a memory resident to or interfaced to a storage device, synchronizer, a communication interface, or non-volatile or volatile memory in communication with a transmitter. A circuit or electronic device designed to send data to another location. The memory may include an ordered listing of executable instructions for implementing logical functions. A logical function or any system element described may be implemented through optic circuitry, digital circuitry, through source code, through analog circuitry, through an analog source such as an analog electrical, audio, or video signal or a combination. The software may be embodied in any computer-readable or signal-bearing medium, for use by, or in connection with an instruction executable system, apparatus, or device. Such a system may include a computer-based system, a processor-containing system, or another system that may selectively fetch instructions from an instruction executable system, apparatus, or device that may also execute instructions.

A “computer-readable medium, ” “machine readable medium, ” “propagated-signal” medium, and/or “signal-bearing medium” may comprise any device that includes stores, communicates, propagates, or transports software for use by or in connection with an instruction executable system, apparatus, or device. The machine-readable medium may selectively be, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, device, or propagation medium. A non-exhaustive list of examples of a machine-readable medium would include: an electrical connection “electronic” having one or more wires, a portable magnetic or optical disk, a volatile memory such as a Random Access Memory “RAM” , a Read-Only Memory “ROM” , an Erasable Programmable Read-Only Memory (EPROM or Flash memory) , or an optical fiber. A machine-readable medium may also include a tangible medium upon which software is printed, as the software may be electronically stored as an image or in another format (e.g., through an optical scan) , then compiled, and/or interpreted or otherwise processed. The processed medium may then be stored in a computer and/or machine memory.

The illustrations of the embodiments described herein are intended to provide a general understanding of the structure of the various embodiments. The illustrations are not intended to serve as a complete description of all of the elements and features of apparatus and systems that utilize the structures or methods described herein. Many other embodiments may be apparent to those of skill in the art upon reviewing the disclosure. Other embodiments may be utilized and derived from the disclosure, such that structural and logical substitutions and changes may be made without departing from the scope of the disclosure. Additionally, the illustrations are merely representational and may not be drawn to scale. Certain proportions within the illustrations may be exaggerated, while other proportions may be minimized. Accordingly, the disclosure and the figures are to be regarded as illustrative rather than restrictive.

One or more embodiments of the disclosure may be referred to herein, individually and/or collectively, by the term “invention” merely for convenience and without intending to voluntarily limit the scope of this application to any particular invention or inventive concept. Moreover, although specific embodiments have been illustrated and described herein, it should be appreciated that any subsequent arrangement designed to achieve the same or similar purpose may be substituted for the specific embodiments shown. This disclosure is intended to cover any and all subsequent adaptations or variations of various embodiments. Combinations of the above embodiments, and other embodiments not specifically described herein, will be apparent to those of skill in the art upon reviewing the description.

The phrase "coupled with" is defined to mean directly connected to or indirectly connected through one or more intermediate components. Such intermediate components may include both hardware and software based components. Variations in the arrangement and type of the components may be made without departing from the spirit or scope of the claims as set forth herein. Additional, different or fewer components may be provided.

The above disclosed subject matter is to be considered illustrative, and not restrictive, and the appended claims are intended to cover all such modifications, enhancements, and other embodiments, which fall within the true spirit and scope of the present invention. Thus, to the maximum extent allowed by law, the scope of the present invention is to be determined by the broadest permissible interpretation of the following claims and their equivalents, and shall not be restricted or limited by the foregoing detailed description. While various embodiments of the invention have been described, it will be apparent to those of ordinary skill in the art that many more embodiments and implementations are possible within the scope of the invention. Accordingly, the invention is not to be restricted except in light of the attached claims and their equivalents.

Claims

A wireless communication method comprising:

receiving measured energy consumption (EC) information for a user equipment (UE) ; and

predicting the EC information for the UE based on the measured EC information.
The method of claim 1, wherein the receiving and the predicting is by a source node, further wherein the UE moves from the source node to a target node or a resource of the UE at the target node is requested to be established or modified by the source node.
The method of claim 2, wherein the source node comprises a core network (CN) and the target node comprises a basestation, or wherein the source node comprises a basestation and the target node comprises another basestation, or wherein the source node comprises a basestation centralized unit and the target node comprises a basestation distributed unit, or wherein the source node comprises a basestation centralized unit control plane and the target node comprises a basestation centralized unit user plane.
The method of claim 2, further comprising:

sending a message to the target node requesting resource allocation for the UE, wherein the message comprises an EC request identification for a request for a report of a previously initiated EC measurement associated with the UE.
The method of claim 4, wherein the message comprises:

a packet data unit (PDU) session setup or modification request message, an initial context setup request message, or a handover request message over NG interface when the source node comprises a core network (CN) ; or

a handover request message, an SN addition request message, or an SN modification request message over Xn interface when the source node is the basestation; or

a context setup request message or a context modification request message over F1 interface when the source node is a centralized unit of the basestation; or

a bearer context setup request message or a bearer context modification request message over E1 interface when the source node is a centralized unit control plane basestation.
The method of claim 2, wherein the measured EC information for the UE comprises at least one of: a source node allocated EC request identification to identify a previously initiated UE EC measurement report or a list of UE identifiers.
The method of claim 2, wherein the measured EC information for the UE comprises at least one of: an energy consumption rate, an energy consumption, or an energy efficiency of network resources used for the UE, a slice of the UE, a quality of service (QoS) flow of the UE, a packet data unit (PDU) session of the UE, or a QoS measurement for a service of the UE.
The method of claim 6, wherein the QoS measurement comprises a packet loss, a data rate, a transmission delay, or a jitter.
The method of claim 1, further comprising:

iteratively reusing the predicted EC information for future predictions.
A wireless communication method comprising:

providing additional user equipment (UE) information; and

receiving a predicted energy consumption (EC) information for the UE based on the additional UE information.
The method of claim 10, wherein the providing and the receiving is by a source node, further wherein the UE is prepared to move from the source node to a target node or a resource of the UE at the target node is prepared to be requested by the source node.
The method of claim 10, wherein the source node comprises a core network (CN) and the target node comprises a basestation, or wherein the source node comprises a basestation and the target node comprises another basestation, or wherein the source node comprises a basestation centralized unit and the target node comprises a basestation distributed unit, or wherein the source node comprises a basestation centralized unit control plane and the target node comprises a basestation centralized unit user plane.
The method of claim 10, further comprising:

sending, by a source node, an EC information request message to a target node, wherein the request comprises the additional UE information; and

receiving, from the target node, a response with the predicted EC information associated with the UE based on the additional UE information.
The method of claim 10, wherein the predicted EC information associated with the UE comprises at least one of:

a list of UE identifier;

a predicted energy consumption rate of the predicted network resources;

a predicted energy consumption of the predicted network resources;

a predicted energy efficiency of the predicted network resources; or

a predicted QoS measurement for a UE's QoS flow;

wherein the predicted network resources comprises a resource predicted to use for a UE, a UE's slice, a UE's PDU session, or a UE's QoS flow.
The method of claim 14, wherein the QoS measurement comprises at least one of a packet loss, a data rate, a transmission delay, or a jitter, wherein the QoS measurement is for a specific service of the UE.
The method of claim 10, wherein the additional UE information comprises at least one of a list of UE identifiers, a target cell identifier, one or more slice identifiers or a quality of service (QoS) flow information of additional services for the UE.
The method of claim 16, wherein the QoS flow information comprises at least one of a QoS identifier, QoS parameters.
The method of claim 16, wherein the additional services comprise QoS flows to be set up at a target node.
A wireless communication method comprising:

providing additional traffic information about a source node; and

receiving a predicted energy consumption (EC) information for the source node based on the additional traffic information.
The method of claim 19, wherein the providing and the receiving is by a source node, further wherein the UE is prepared to move from the source node to a target node or a resource of the UE at the target node is prepared to be requested by the source node.
The method of claim 20, wherein the source node comprises a core network (CN) and the target node comprises a basestation, or wherein the source node comprises a basestation and the target node comprises another basestation, or wherein the source node comprises a basestation centralized unit and the target node comprises a basestation distributed unit, or wherein the source node comprises a basestation centralized unit control plane and the target node comprises a basestation centralized unit user plane.
The method of claim 20, wherein the additional traffic information comprises at least one of information for a specific cell, a specific slice, the node, additional UE number, additional RRC connection number, additional PRB number, additional specific type of QoS flow number, additional traffic load, or additional data rate.
The method of claim 20, wherein when the target node receives the additional traffic information within an EC information request message sent by the source node, the target node provides the predicted EC information associated with source node based on the additional traffic information.
The method of claim 23, wherein the predicted EC information is based on both current traffic and the additional traffic information, further wherein a predicted change to the EC information is based on the additional traffic information.
The method of claim 23, wherein the predicted EC information comprises a predicted change in an energy consumption rate, a predicted change in an energy consumption, a predicted change in an energy efficiency, or a predicted change in an average quality of service (QoS) measurement.
The method of claim 25, wherein the QoS measurement comprises a packet loss, a data rate a, transmission delay, or a jitter for a specific service or QoS flow for a specific cell, a specific slice, or an entirety of the node.
The method of claim 20, wherein when the target node does not receive the additional traffic information within the EC information request message sent by the source node, the target node provides the predicted EC information using a historical measured traffic information.
The method of claim 20, wherein when the target node does not receive the additional traffic information within the EC information request message sent by the source node, the target node provides a measured EC information associated with node, wherein the measured EC information comprises at least one of the following: a measured energy consumption rate, a measured energy consumption, a measured energy efficiency, or a measured average quality of service (QoS) measurement.
A wireless communications apparatus comprising a processor and a memory, wherein the processor is configured to read code from the memory and implement a method recited in any of claims 1 to 28.
A computer program product comprising a computer-readable program medium code stored thereupon, the code, when executed by a processor, causing the processor to implement a method recited in any of claims 1 to 28.