WO2024211680A1

WO2024211680A1 - Management of machine learning entity inference emulation in a cellular network

Info

Publication number: WO2024211680A1
Application number: PCT/US2024/023235
Authority: WO
Inventors: Yizhi Yao; Joey Chou
Original assignee: Intel Corp
Current assignee: Intel Corp
Priority date: 2023-04-05
Filing date: 2024-04-05
Publication date: 2024-10-10
Anticipated expiration: 2025-10-05

Abstract

A device, a method, a system and one or more computer-readable media. A first example device is to host a management service (MnS) producer for a wireless cellular network. One or more processors of the first device are to receive, from an MnS consumer, a request to perform AI/ML emulation in one or more available machine learning (ML) emulation environments; and send to the MnS consumer one or more instances of an information object class (IOC) associated with the process of the AI/ML emulation. A second example device is to host an MnS consumer. One or more processors of the second device are to send, to an MnS producer, a request to perform AI/ML emulation in one or more available machine learning (ML) emulation environments; and receive, from the MnS producer one or more instances of an information object class (IOC) associated with the process of the AI/ML emulation.

Description

MANAGEMENT OF MACHINE LEARNING ENTITY INFERENCE EMULATION IN A CELLULAR NETWORK

CROSS REFERENCE TO RELATED APPLICATIONS

[0001] This application claims the benefit of and priority from U.S. Provisional Patent Application No. 63/494,429 entitled " MANAGEMENT OF MACHINE LEARNING ENTITY INFERENCE EMULATION” filed April 5, 2023, the entire disclosure of which is incorporated herein by reference.

BACKGROUND

[0002] After a machine learning (ML) entity is trained in a wireless network, such as a cellular wireless network, validation is performed to ensure the ML training process is completed successfully. Typically, validation is performed by preserving part of the training data set and using it after training to check performance of the ML entity when it is running on the validation data. Improvements are needed with respect to the ML process in cellular environments.

BRIEF DESCRIPTION OF THE DRAWINGS

[0003] Fig. 1 illustrates a ML entity inference emulation environment including a management and orchestration of network and services (MnS) producer and an MnS consumer.

[0004] Fig. 2 illustrates according to an embodiment, a software diagram of information object class dependencies for artificial intelligence (AI)/machine learning (ML) emulation for network resource management (NRM).on

[0005] Fig. 3A illustrates a process be performed at a management service (MnS) consumer in a wireless cellular network according to some embodiments.

[0006] Fig. 3B illustrates a process be performed at a MnS producer for a wireless cellular network according to some embodiments.

[0007] Fig. 4 illustrates a communication network according to some embodiments.

[0008] Fig. 5 illustrates another communication system based on cellular communications according to some embodiments. [0009] Fig. 6 illustrates a block diagram illustrating components, according to some example embodiments, able to read instructions from a machine-readable or computer-readable medium and perform any one or more of the methodologies discussed herein.

[0010] Fig. 7 illustrates a simplified block diagram of artificial (Al)-assisted communication between a User Equipment (UE) and a Radio Access Network (RAN) according to some embodiments.

DETAILED DESCRIPTION

[0011] The following detailed description refers to the accompanying drawings. The same reference numbers may be used in different drawings to identify the same or similar elements. In the following description, for purposes of explanation and not limitation, specific details are set forth such as particular structures, architectures, interfaces, techniques, etc. in order to provide a thorough understanding of the various aspects of various embodiments. However, it will be apparent to those skilled in the art having the benefit of the present disclosure that the various aspects of the various embodiments may be practiced in other examples that depart from these specific details. In certain instances, descriptions of well-known devices, circuits, and methods are omitted so as not to obscure the description of the various embodiments with unnecessary detail. For the purposes of the present document, the phrases “A or B” and “A/B” mean (A), (B), or (A and B).

[0012] Some embodiments propose inference emulation to be performed using the ML entity after validation of the ML training process. Inference emulation, as opposed to validation, uses real time data in a runtime environment, as opposed to training data as used by validation. A runtime environment during inference emulation may be referred to as an emulation environment. Inference emulation, as opposed to merely inference by itself, uses data from a runtime environment that does not correspond to a network in practical operation (a network being used for the purpose actual communication). Inference emulation uses data from a network in operation with real time data, for the purpose of executing an emulation algorithm to test the advantages and disadvantages of a ML engine. Inference by itself, however, is a broader term that refers to ML/ Al inferences in a real network, that is, one in practical operation. [0013] According to an embodiment, the ML entity may be either an ML model or an entity containing an ML model and its related metadata. The ML entity may be implemented by an operator or management system.

[0014] According to an embodiment, after the ML entity is validated during development, inference emulation may be deployed to check if the ML entity is working correctly under certain runtime context in the emulation environment, before applying the ML entity in the real live network or system.

[0015] Validation data, on the other hand, refers to a portion of the training dataset that is set aside for evaluating the performance of the ML model after training. By using this data, one may assess how well the ML model performs in real-world scenarios and verify that the training process was successful.

[0016] Advantageously, an emulation process according to some embodiments aims to ensure that the ML entity operates correctly under specific runtime conditions before ML is deployed in a live environment.

[0017] According to an embodiment, referring to Fig. 1, in a ML entity inference emulation environment 100, a management and orchestration of network and services (MnS) producer 102 may have the capabilities and may provide the services needed to enable a MnS consumer 104 to request inference emulation from the MnS producer 102, and/or to monitor the progress and the performance of the ML entity during the inference emulation, as will be explained in further detail below.

[0018] The MnS producer 102 may for example be hosted in a management system above and separate from a New Radio (NR) node B (gNodeB), on a gNB itself or on any other system capable of hosting the same. The MnS consumer 104 may be hosting on a server, on a core network (CN), on a gNodeB, or on any other system capable of hosting the same.

[0019] Various embodiments herein provide solutions for management of artificial intelligencemachine learning (ALML) entity emulation. Embodiments may relate to a wireless cellular network, e.g., as standardized by way of the Third Generation Partnership Project (3GPP), such as a 5G (New Radio), 6G or other network.

[0020] Embodiments are described herein using example names of attributes or information elements. However, these are merely examples, and other names for the attributes and/or information elements may be used. [0021] Some embodiments build upon relevant information provided in 3GPP Technical Specification (TS) 28.105 V17.3.0 (2023-03) for “AI/ML management,” and on 3GPP TR 28.908: "Study on AI/ML management" V17.3.0 (2023-03).

[0022] 1. Use case and requirements for management of ML entity inference emulation [0023] 1.1 Managing ML Inference emulation

[0024] According to some embodiments, the 3 GPP management system may have resources for multiple emulation environments to be used depending on network needs. These may include simulation environments, a digital twin of the network (i.e., a digital copy of the network), a test network or the real network under certain constrained conditions, for example for a selected set of user equipments (UEs). The multiple emulation environments may represent different levels of trust that the operator or management system has in the ML entity or AI/ML inference functions. Correspondingly, 3GPP management system needs to have capabilities for managing the inference emulation.

[0025] According to some embodiments, the emulation management process may include the MnS consumer querying the MnS producer regarding the latter’s available emulation environments, and choosing the right type and instance of an emulation environment for the right AI/ML inference emulation function by an ML entity.

[0026] According to some embodiments, the emulation process may also involve the control of execution of an AI/ML inference emulation function by an ML entity, for example, by implementing control of an ML entity, for example to execute an ML inference emulation function only within certain hours, or only on cells with a particular kind of load, or only on cells in a particular area or in limited subscriber groups.

[0027] According to some embodiments, the services provided by the inference emulation MnS producer may include: providing available emulation environment(s) to the MnS consumer; allowing the MnS consumer to choose or select an emulation environment for the emulation of one or more ML entities based on the available emulation environment s); allowing the MnS consumer to control the emulation process for the ML entity, such as starting of the emulation process, stopping the emulation process, suspending the emulation process and/or resuming the emulation process; allowing the MnS consumer to activate/deactivate an ML entity during the emulation (i.e., to trigger execution of/to halt execution of an ML entity during the emulation process); and/or allowing the MnS consumer to monitor the inference performance of the ML entities during the emulation.

[0028] 1.2 Requirements

[0029] The below signaling corresponds to communications between the MnS producer and the MnS consumer, in a direction as specified more particularly below. The communications may take place using Representational State Transfer (REST) within RESTful system that uses the Hypertext Transfer Protocol.

[0030] According to some embodiments, one or more of the below communications may take place between the MnS producer and the MnS consumer, with the direction indicated on the per communication basis, and keeping in mind that the noted suggested name of the communication provided in quotes below is merely an example:

[0031] According to one embodiment, an authorized MnS consumer may send to a MnS producer a communication, for example “REQ-AI/ML EMUL-l,” that corresponds to a query from the MnS consumer to the MnS producer regarding (i.e., to ask about) available emulation environments at the MnS producer.

[0032] According to one embodiment, an authorized MnS consumer may send to a MnS producer a communication, for example “REQ-AI/ML_EMUL-2,” that corresponds to a request from the MnS consumer to the MnS producer regarding an ML inference emulation for a specific ML entity at a selected emulation environment .

[0033] According to one embodiment, an MnS producer may send to an authorized MnS consumer a communication, for example “REQ-AI/ML_EMUL-3,” that corresponds to information to the authorized MnS consumer about the status of the emulation of an ML entity. The status may indicate, for example, whether the ML entity is at its start, is running, is suspended, or has stopped.

[0034] According to one embodiment, an authorized MnS consumer (e.g., an operator) may send to MnS producer a communication, for example “REQ-AI/ML_EMUL-4,” that corresponds to information to implement control of the ML emulation process, such as information to cause starting, suspending or restarting the emulation. Control may further include, by way of example and in the context of ML emulation, executing an ML inference emulation function only within certain hours, or only on cells with a particular kind of load, or only on cells in a particular area or in limited subscriber groups.

[0035] According to one embodiment, an authorized MnS consumer (e.g., an operator) may send to an MnS producer a communication, for example “REQ-AI/ML_EMUL-5,” that corresponds to information to activate and deactivate an ML entity during the emulation. In particular, emulation may involve the simultaneous running of multiple ML entities or models. The communication to activate or deactivate may be to activate or deactivate a given one of the multiple ML entities running simultaneously.

[0036] According to one embodiment, an authorized MnS consumer (e.g., an operator) may send to an MnS producer a communication, for example “REQ-AI/ML_EMUL-6,” that corresponds to a request to the MnS producer to report an outcome of an emulation process.

[0037] 2. Solution for management of ML entity inference emulation

[0038] Some embodiments propose a solution that uses instances of the following Information Object Classes (IOCS), attributes and performance data for interaction between MnS producer and MnS consumer to support the ML inference emulation:

1) The IOC representing the available emulation environment, may be named Avail abl eEmul ati onEnvironment :

According to an embodiment, the instance of this IOC may be created by the MnS producer to allow the MnS consumer to query, or be informed of, the information of the available emulation environments. This IOC may contain the following attributes:

- description of the emulation environment, such as supported features, corresponding 3GPP release number, number of cells, etc.; and/or

- available resources (e.g., processing resources, memory resources, etc.).

2) The IOC representing the emulation request may be named EmulationRequest:

The instance of this IOC may be created by the MnS consumer onto the MnS producer, to send the emulation request. This IOC may contain the following attributes:

- identifier of the ML entities requested for emulation;

- identifier of the selected emulation environment; and/or

- time window for the emulation.

3) The IOC representing the emulation process may be named EmulationProcess. The instance of this TOC may be created by the MnS producer, to allow the MnS consumer to be informed of, and control, the emulation progress. This IOC may contain the following attributes:

- progress indicator for the emulation process;

- the identifier of the corresponding emulation request; and/or

- an attribute for controlling the emulation process, such as starting, stopping, suspending, and resuming.

4) According to some embodiments, the TOCs and attributes for the solutions of AI/ML activation for the ML inference phase (as described in clause 5.2.7.4.2 of TR 28.908 VI .1.0 (2023-03)), may, according to an embodiment, be reused for activating and deactivating ML entities during emulation.

5) According to some embodiments, the TOCs, attributes and performance measurements for the solutions of performance evaluation for AI/ML inference for inference phase (as described in clause 5.2.6.4 of TR 28.908 VI.1.0 (2023-03)), can be reused for monitoring the inference performance of the ML entities during the emulation.

[0039] Reference is now made to Fig. 2, which shows a software diagram 200 of IOC dependencies for AI/ML emulation for network resource management (NRM), including the IOC AvailableEmulationEnvironment 202, the IOC EmulationRequest 204, and the IOC EmulationProcess 206. The arrows represent relationships or associations between different elements and in this case IOCS. Tn the context of information object classes and instances, the shown solid arrows indicate a relationship or association between classes. For example, the arrow 208 pointing from IOC 206 to IOC 204 signifies that instances of IOC EmulationProcess 206 contain or reference instances of IOC EmulationRequest 204. For example, the arrow 210 pointing from IOC 204 to IOC 202 signifies that instances of IOC EmulationRequest 204 contain or reference instances of IOC AvailableEmulationEnvironment 202. The asterisks shown in Fig. 2 denote multiplicity or cardinality, indicating how many instances of one class are related to instances of another class through a particular association. For instance, the single asterisk next to IOC EmulationProcess 206 indicates a one-to-one relationship meaning that each instance of the IOC EmulationProcess 206 is associated with one instance of IOC EmulationRequest 204. The integer 1 in this context often represent specific values or ranges, particularly related to cardinality or multiplicity. For example, the integer 1 represents exact cardinalities, indicating that a certain number of instances of one class are associated with instances of another class. [0040] Fig. 3A shows a process 300A according to some embodiments. Process 300A to be performed at a management service (MnS) consumer in a wireless cellular network. Process 300A includes, at operation 302A, sending, to an MnS producer, a request to query information about one or more available machine learning (ML) emulation environments. Process 300A includes, at operation 304 A, receiving, from the MnS producer one or more instances of an information object class (IOC) associated with respective ones of the one or more available emulation environments.

[0041] Fig. 3B shows a process 300B according to some embodiments. Process 300B to be performed at a management service (MnS) producer for a wireless cellular network. Process 300B includes, at operation 302B, receiving, from an MnS consumer, a request to query information about one or more available machine learning (ML) emulation environments. Process 300B includes, at operation 304B, sending to the MnS consumer one or more instances of an information object class (IOC) associated with respective ones of the one or more available emulation environments.

[0042] Systems and Implementations

[0043] Figures 4-7 illustrate various systems, devices, and components that may implement aspects of disclosed embodiments.

[0044] Fig. 4 illustrates a network 400 in accordance with various embodiments. The network 400 may operate in a manner consistent with 3GPP technical specifications for LTE or 5G/NR systems. However, the example embodiments are not limited in this regard and the described embodiments may apply to other networks that benefit from the principles described herein, such as future 3 GPP systems, or the like.

[0045] The network 400 may include a UE 402, which may include any mobile or non-mobile computing device designed to communicate with a RAN 404 via an over-the-air connection. The UE 402 may be communicatively coupled with the RAN 404 by a Uu interface. The UE 402 may be, but is not limited to, a smartphone, tablet computer, wearable computer device, desktop computer, laptop computer, in-vehicle infotainment, in-car entertainment device, instrument cluster, head-up display device, onboard diagnostic device, dashtop mobile equipment, mobile data terminal, electronic engine management system, electronic/engine control unit, electronic/engine control module, embedded system, sensor, microcontroller, control module, engine management system, networked appliance, machine-type communication device, M2M or D2D device, loT device, etc.

[0046] In some embodiments, the network 400 may include a plurality of UEs coupled directly with one another via a sidelink interface. The UEs may be M2M/D2D devices that communicate using physical sidelink channels such as, but not limited to, PSBCH, PSDCH, PSSCH, PSCCH, PSFCH, etc.

[0047] In some embodiments, the UE 402 may additionally communicate with an AP 406 via an over-the-air connection. The AP 406 may manage a WLAN connection, which may serve to offload some/all network traffic from the RAN 404. The connection between the UE 402 and the AP 406 may be consistent with any IEEE 802.11 protocol, wherein the AP 406 could be a wireless fidelity (Wi-Fi®) router. In some embodiments, the UE 402, RAN 404, and AP 406 may utilize cellular- WLAN aggregation (for example, LWA/LWIP). Cellular- WLAN aggregation may involve the UE 402 being configured by the RAN 404 to utilize both cellular radio resources and WLAN resources.

[0048] The RAN 404 may include one or more access nodes, for example, AN 408. AN 408 may terminate air-interface protocols for the UE 402 by providing access stratum protocols including RRC, PDCP, RLC, MAC, and LI protocols. In this manner, the AN 408 may enable data/voice connectivity between CN 420 and the UE 402. In some embodiments, the AN 408 may be implemented in a discrete device or as one or more software entities running on server computers as part of, for example, a virtual network, which may be referred to as a CRAN or virtual baseband unit pool. The AN 408 be referred to as a BS, gNB, RAN node, eNB, ng-eNB, NodeB, RSU, TRxP, TRP, etc. The AN 408 may be a macrocell base station or a low power base station for providing femtocells, picocells or other like cells having smaller coverage areas, smaller user capacity, or higher bandwidth compared to macrocells.

[0049] In embodiments in which the RAN 404 includes a plurality of ANs, they may be coupled with one another via an X2 interface (if the RAN 404 is an LTE RAN) or an Xn interface (if the RAN 404 is a 5G RAN). The X2/Xn interfaces, which may be separated into control/user plane interfaces in some embodiments, may allow the ANs to communicate information related to handovers, data/context transfers, mobility, load management, interference coordination, etc. [0050] The ANs of the RAN 404 may each manage one or more cells, cell groups, component carriers, etc. to provide the UE 402 with an air interface for network access. The UE 402 may be simultaneously connected with a plurality of cells provided by the same or different ANs of the RAN 404. For example, the UE 402 and RAN 404 may use carrier aggregation to allow the UE 402 to connect with a plurality of component carriers, each corresponding to a Pcell or Scell. In dual connectivity scenarios, a first AN may be a master node that provides an MCG and a second AN may be secondary node that provides an SCG. The first/second ANs may be any combination of eNB, gNB, ng-eNB, etc.

[0051] The RAN 404 may provide the air interface over a licensed spectrum or an unlicensed spectrum. To operate in the unlicensed spectrum, the nodes may use LAA, eLAA, and/or feLAA mechanisms based on CA technology with PCells/Scells. Prior to accessing the unlicensed spectrum, the nodes may perform medium/carrier-sensing operations based on, for example, a listen-before-talk (LBT) protocol.

[0052] In V2X scenarios the UE 402 or AN 408 may be or act as a RSU, which may refer to any transportation infrastructure entity used for V2X communications. An RSU may be implemented in or by a suitable AN or a stationary (or relatively stationary) UE. An RSU implemented in or by: a UE may be referred to as a “UE-type RSU”; an eNB may be referred to as an “eNB-type RSU”; a gNB may be referred to as a “gNB-type RSU”; and the like. In one example, an RSU is a computing device coupled with radio frequency circuitry located on a roadside that provides connectivity support to passing vehicle UEs. The RSU may also include internal data storage circuitry to store intersection map geometry, traffic statistics, media, as well as applications/software to sense and control ongoing vehicular and pedestrian traffic. The RSU may provide very low latency communications required for high speed events, such as crash avoidance, traffic warnings, and the like. Additionally or alternatively, the RSU may provide other cellular/WLAN communications services. The components of the RSU may be packaged in a weatherproof enclosure suitable for outdoor installation, and may include a network interface controller to provide a wired connection (e.g., Ethernet) to a traffic signal controller or a backhaul network.

[0053] In some embodiments, the RAN 404 may be an LTE RAN 410 with eNBs, for example, eNB 412. The LTE RAN 410 may provide an LTE air interface with the following characteristics: SCS of 15 kHz; CP-OFDM waveform for DL and SC-FDMA waveform for UL; turbo codes for data and TBCC for control; etc. The LTE air interface may rely on CSI-RS for CSI acquisition and beam management; PDSCH/PDCCH DMRS for PDSCH/PDCCH demodulation; and CRS for cell search and initial acquisition, channel quality measurements, and channel estimation for coherent demodulation/detection at the UE. The LTE air interface may operate on sub-6 GHz bands.

[0054] In some embodiments, the RAN 404 may be an NG-RAN 414 with gNBs, for example, gNB 416, or ng-eNBs, for example, ng-eNB 418. The gNB 416 may connect with 5G-enabled UEs using a 5G NR interface. The gNB 416 may connect with a 5G core through an NG interface, which may include an N2 interface or an N3 interface. The ng-eNB 418 may also connect with the 5G core through an NG interface, but may connect with a UE via an LTE air interface. The gNB 416 and the ng-eNB 418 may connect with each other over an Xn interface. [0055] In some embodiments, the NG interface may be split into two parts, an NG user plane (NG-U) interface, which carries traffic data between the nodes of the NG-RAN 414 and a UPF 448 (e.g., N3 interface), and an NG control plane (NG-C) interface, which is a signaling interface between the nodes of the NG-RAN414 and an AMF 444 (e.g., N2 interface).

[0056] The NG-RAN 414 may provide a 5G-NR air interface with the following characteristics: variable SCS; CP-OFDM for DL, CP-OFDM and DFT-s-OFDM for UL; polar, repetition, simplex, and Reed-Muller codes for control and LDPC for data. The 5G-NR air interface may rely on CSI-RS, PDSCH/PDCCH DMRS similar to the LTE air interface. The 5G-NR air interface may not use a CRS, but may use PBCH DMRS for PBCH demodulation; PTRS for phase tracking for PDSCH; and tracking reference signal for time tracking. The 5G-NR air interface may operate on FR1 bands that include sub-6 GHz bands or FR2 bands that include bands from 24.25 GHz to 52.6 GHz. The 5G-NR air interface may include an SSB that is an area of a downlink resource grid that includes PSS/SSS/PBCH.

[0057] In some embodiments, the 5G-NR air interface may utilize BWPs for various purposes. For example, BWP can be used for dynamic adaptation of the SCS. For example, the UE 402 can be configured with multiple BWPs where each BWP configuration has a different SCS. When a BWP change is indicated to the UE 402, the SCS of the transmission is changed as well. Another use case example of BWP is related to power saving. In particular, multiple BWPs can be configured for the UE 402 with different amount of frequency resources (for example, PRBs) to support data transmission under different traffic loading scenarios. A BWP containing a smaller number of PRBs can be used for data transmission with small traffic load while allowing power saving at the UE 402 and in some cases at the gNB 416. A BWP containing a larger number of PRBs can be used for scenarios with higher traffic load.

[0058] The RAN 404 is communicatively coupled to CN 420 that includes network elements to provide various functions to support data and telecommunications services to customers/subscribers (for example, users of UE 402). The components of the CN 420 may be implemented in one physical node or separate physical nodes. In some embodiments, NFV may be utilized to virtualize any or all of the functions provided by the network elements of the CN 420 onto physical compute/storage resources in servers, switches, etc. A logical instantiation of the CN 420 may be referred to as a network slice, and a logical instantiation of a portion of the CN 420 may be referred to as a network sub-slice.

[0059] In some embodiments, the CN 420 may be an LTE CN 422, which may also be referred to as an EPC. The LTE CN 422 may include MME 424, SGW 426, SGSN 428, HSS 430, PGW 432, and PCRF 434 coupled with one another over interfaces (or “reference points”) as shown. Functions of the elements of the LTE CN 422 may be briefly introduced as follows.

[0060] The MME 424 may implement mobility management functions to track a current location of the UE 402 to facilitate paging, bearer activation/deactivation, handovers, gateway selection, authentication, etc.

[0061] The SGW 426 may terminate an SI interface toward the RAN and route data packets between the RAN and the LTE CN 422. The SGW 426 may be a local mobility anchor point for inter-RAN node handovers and also may provide an anchor for inter-3GPP mobility. Other responsibilities may include lawful intercept, charging, and some policy enforcement.

[0062] The SGSN 428 may track a location of the UE 402 and perform security functions and access control. In addition, the SGSN 428 may perform inter-EPC node signaling for mobility between different RAT networks; PDN and S-GW selection as specified by MME 424; MME selection for handovers; etc. The S3 reference point between the MME 424 and the SGSN 428 may enable user and bearer information exchange for inter-3GPP access network mobility in idle/active states.

[0063] The HSS 430 may include a database for network users, including subscription-related information to support the network entities’ handling of communication sessions. The HSS 430 can provide support for routing/roaming, authentication, authorization, naming/addressing resolution, location dependencies, etc. An S6a reference point between the HSS 430 and the MME 424 may enable transfer of subscription and authentication data for authenticating/authorizing user access to the LTE CN 420.

[0064] The PGW 432 may terminate an SGi interface toward a data network (DN) 436 that may include an application/content server 438. The PGW 432 may route data packets between the LTE CN 422 and the data network 436. The PGW 432 may be coupled with the SGW 426 by an S5 reference point to facilitate user plane tunneling and tunnel management. The PGW 432 may further include a node for policy enforcement and charging data collection (for example, PCEF). Additionally, the SGi reference point between the PGW 432 and the data network YX 36 may be an operator external public, a private PDN, or an intra-operator packet data network, for example, for provision of IMS services. The PGW 432 may be coupled with a PCRF 434 via a Gx reference point.

[0065] The PCRF 434 is the policy and charging control element of the LTE CN 422. The PCRF 434 may be communicatively coupled to the app/content server 438 to determine appropriate QoS and charging parameters for service flows. The PCRF 434 may provision associated rules into a PCEF (via Gx reference point) with appropriate TFT and QCI.

[0066] In some embodiments, the CN 420 may be a 5GC 440. The 5GC 440 may include an AUSF 442, AMF 444, SMF 446, UPF 448, NSSF 450, NEF 452, NRF 454, PCF 456, UDM 458, and AF 460 coupled with one another over interfaces (or “reference points”) as shown. Functions of the elements of the 5GC 440 may be briefly introduced as follows.

[0067] The AUSF 442 may store data for authentication of UE 402 and handle authentication- related functionality. The AUSF 442 may facilitate a common authentication framework for various access types. In addition to communicating with other elements of the 5GC 440 over reference points as shown, the AUSF 442 may exhibit an Nausf service-based interface.

[0068] The AMF 444 may allow other functions of the 5GC 440 to communicate with the UE 402 and the RAN 404 and to subscribe to notifications about mobility events with respect to the UE 402. The AMF 444 may be responsible for registration management (for example, for registering UE 402), connection management, reachability management, mobility management, lawful interception of AMF-related events, and access authentication and authorization. The AMF 444 may provide transport for SM messages between the UE 402 and the SMF 446, and act as a transparent proxy for routing SM messages. AMF 444 may also provide transport for SMS messages between UE 402 and an SMSF. AMF 444 may interact with the AUSF 442 and the UE 402 to perform various security anchor and context management functions. Furthermore, AMF 444 may be a termination point of a RAN CP interface, which may include or be an N2 reference point between the RAN 404 and the AMF 444; and the AMF 444 may be a termination point of NAS (Nl) signaling, and perform NAS ciphering and integrity protection. AMF 444 may also support NAS signaling with the UE 402 over an N3 IWF interface.

[0069] The SMF 446 may be responsible for SM (for example, session establishment, tunnel management between UPF 448 and AN 408); UE IP address allocation and management (including optional authorization); selection and control of UP function; configuring traffic steering at UPF 448 to route traffic to proper destination; termination of interfaces toward policy control functions; controlling part of policy enforcement, charging, and QoS; lawful intercept (for SM events and interface to LI system); termination of SM parts of NAS messages; downlink data notification; initiating AN specific SM information, sent via AMF 444 over N2 to AN 408; and determining SSC mode of a session. SM may refer to management of a PDU session, and a PDU session or “session” may refer to a PDU connectivity service that provides or enables the exchange of PDUs between the UE 402 and the data network 436.

[0070] The UPF 448 may act as an anchor point for intra-RAT and inter-RAT mobility, an external PDU session point of interconnect to data network 436, and a branching point to support multi-homed PDU session. The UPF 448 may also perform packet routing and forwarding, perform packet inspection, enforce the user plane part of policy rules, lawfully intercept packets (UP collection), perform traffic usage reporting, perform QoS handling for a user plane (e.g., packet filtering, gating, UL/DL rate enforcement), perform uplink traffic verification (e.g., SDF- to-QoS flow mapping), transport level packet marking in the uplink and downlink, and perform downlink packet buffering and downlink data notification triggering. UPF 448 may include an uplink classifier to support routing traffic flows to a data network.

[0071] The NSSF 450 may select a set of network slice instances serving the UE 402. The NSSF 450 may also determine allowed NSSAI and the mapping to the subscribed S-NSSAIs, if needed. The NSSF 450 may also determine the AMF set to be used to serve the UE 402, or a list of candidate AMFs based on a suitable configuration and possibly by querying the NRF 454. The selection of a set of network slice instances for the UE 402 may be triggered by the AMF 444 with which the UE 402 is registered by interacting with the NSSF 450, which may lead to a change of AMF The NSSF 450 may interact with the AMF 444 via an N22 reference point; and may communicate with another NSSF in a visited network via an N31 reference point (not shown). Additionally, the NSSF 450 may exhibit an Nnssf service-based interface.

[0072] The NEF 452 may securely expose services and capabilities provided by 3GPP network functions for third party, internal exposure/re-exposure, AFs (e.g., AF 460), edge computing or fog computing systems, etc. In such embodiments, the NEF 452 may authenticate, authorize, or throttle the AFs. NEF 452 may also translate information exchanged with the AF 460 and information exchanged with internal network functions. For example, the NEF 452 may translate between an AF-Service-Identifier and an internal 5GC information. NEF 452 may also receive information from other NFs based on exposed capabilities of other NFs. This information may be stored at the NEF 452 as structured data, or at a data storage NF using standardized interfaces. The stored information can then be re-exposed by the NEF 452 to other NFs and AFs, or used for other purposes such as analytics. Additionally, the NEF 452 may exhibit an Nnef service-based interface.

[0073] The NRF 454 may support service discovery functions, receive NF discovery requests from NF instances, and provide the information of the discovered NF instances to the NF instances. NRF 454 also maintains information of available NF instances and their supported services. As used herein, the terms “instantiate,” “instantiation,” and the like may refer to the creation of an instance, and an “instance” may refer to a concrete occurrence of an object, which may occur, for example, during execution of program code. Additionally, the NRF 454 may exhibit the Nnrf service-based interface.

[0074] The PCF 456 may provide policy rules to control plane functions to enforce them, and may also support unified policy framework to govern network behavior. The PCF 456 may also implement a front end to access subscription information relevant for policy decisions in a UDR of the UDM 458. In addition to communicating with functions over reference points as shown, the PCF 456 exhibit an Npcf service-based interface.

[0075] The UDM 458 may handle subscription-related information to support the network entities’ handling of communication sessions, and may store subscription data of UE 402. For example, subscription data may be communicated via an N8 reference point between the UDM 458 and the AMF 444. The UDM 458 may include two parts, an application front end and a UDR. The UDR may store subscription data and policy data for the UDM 458 and the PCF 456, and/or structured data for exposure and application data (including PFDs for application detection, application request information for multiple UEs 402) for the NEF 452. The Nudr service-based interface may be exhibited by the UDR 221 to allow the UDM 458, PCF 456, and NEF 452 to access a particular set of the stored data, as well as to read, update (e.g., add, modify), delete, and subscribe to notification of relevant data changes in the UDR. The UDM may include a UDM-FE, which is in charge of processing credentials, location management, subscription management and so on. Several different front ends may serve the same user in different transactions. The UDM-FE accesses subscription information stored in the UDR and performs authentication credential processing, user identification handling, access authorization, registration/mobility management, and subscription management. In addition to communicating with other NFs over reference points as shown, the UDM 458 may exhibit the Nudm servicebased interface.

[0076] The AF 460 may provide application influence on traffic routing, provide access to NEF, and interact with the policy framework for policy control.

[0077] In some embodiments, the 5GC 440 may enable edge computing by selecting operator/3rd party services to be geographically close to a point that the UE 402 is attached to the network. This may reduce latency and load on the network. To provide edge-computing implementations, the 5GC 440 may select a UPF 448 close to the UE 402 and execute traffic steering from the UPF 448 to data network 436 via the N6 interface. This may be based on the UE subscription data, UE location, and information provided by the AE 460. In this way, the AF 460 may influence UPF (re)selection and traffic routing. Based on operator deployment, when AF 460 is considered to be a trusted entity, the network operator may permit AF 460 to interact directly with relevant NFs. Additionally, the AF 460 may exhibit an Naf service-based interface. [0078] The data network 436 may represent various network operator services, Internet access, or third party services that may be provided by one or more servers including, for example, application/content server 438.

[0079] Fig. 5 illustrates a wireless network 500 in accordance with various embodiments. The wireless network 500 may include a UE 502 in wireless communication with an AN 504. The UE 502 and AN 504 may be similar to, and substantially interchangeable with, like-named components described elsewhere herein. [0080] The UE 502 may be communicatively coupled with the AN 504 via connection 506. The connection 506 is illustrated as an air interface to enable communicative coupling, and can be consistent with cellular communications protocols such as an LTE protocol or a 5G NR protocol operating at mmWave or sub-6GHz frequencies.

[0081] The UE 502 may include a host platform 508 coupled with a modem platform 510. The host platform 508 may include application processing circuitry 512, which may be coupled with protocol processing circuitry 514 of the modem platform 510. The application processing circuitry 512 may run various applications for the UE 502 that source/sink application data. The application processing circuitry 512 may further implement one or more layer operations to transmit/receive application data to/from a data network. These layer operations may include transport (for example UDP) and Internet (for example, IP) operations

[0082] The protocol processing circuitry 514 may implement one or more of layer operations to facilitate transmission or reception of data over the connection 506. The layer operations implemented by the protocol processing circuitry 514 may include, for example, MAC, RLC, PDCP, RRC and NAS operations.

[0083] The modem platform 510 may further include digital baseband circuitry 516 that may implement one or more layer operations that are “below” layer operations performed by the protocol processing circuitry 514 in a network protocol stack. These operations may include, for example, PHY operations including one or more of HARQ-ACK functions, scrambling/descrambling, encoding/decoding, layer mapping/de-mapping, modulation symbol mapping, received symbol/bit metric determination, multi-antenna port precoding/decoding, which may include one or more of space-time, space-frequency or spatial coding, reference signal generation/detection, preamble sequence generation and/or decoding, synchronization sequence generation/detection, control channel signal blind decoding, and other related functions.

[0084] The modem platform 510 may further include transmit circuitry 518, receive circuitry 520, RF circuitry 522, and RF front end (RFFE) 524, which may include or connect to one or more antenna panels 526. Briefly, the transmit circuitry 518 may include a digital-to-analog converter, mixer, intermediate frequency (IF) components, etc.; the receive circuitry 520 may include an analog-to-digital converter, mixer, IF components, etc.; the RF circuitry 522 may include a low-noise amplifier, a power amplifier, power tracking components, etc.; RFFE 524 may include filters (for example, surface/bulk acoustic wave filters), switches, antenna tuners, beamforming components (for example, phase-array antenna components), etc. The selection and arrangement of the components of the transmit circuitry 518, receive circuitry 520, RF circuitry 522, RFFE 524, and antenna panels 526 (referred generically as “transmit/receive components”) may be specific to details of a specific implementation such as, for example, whether communication is TDM or FDM, in mmWave or sub-6 gHz frequencies, etc. In some embodiments, the transmit/receive components may be arranged in multiple parallel transmit/receive chains, may be disposed in the same or different chips/modules, etc.

[0085] In some embodiments, the protocol processing circuitry 514 may include one or more instances of control circuitry (not shown) to provide control functions for the transmit/receive components.

[0086] A UE reception may be established by and via the antenna panels 526, RFFE 524, RF circuitry 522, receive circuitry 520, digital baseband circuitry 516, and protocol processing circuitry 514. In some embodiments, the antenna panels 526 may receive a transmission from the AN 504 by receive-beamforming signals received by a plurality of antennas/antenna elements of the one or more antenna panels 526.

[0087] A UE transmission may be established by and via the protocol processing circuitry 514, digital baseband circuitry 516, transmit circuitry 518, RF circuitry 522, RFFE 524, and antenna panels 526. In some embodiments, the transmit components of the UE 502 may apply a spatial filter to the data to be transmitted to form a transmit beam emitted by the antenna elements of the antenna panels 526.

[0088] Similar to the UE 502, the AN 504 may include a host platform 528 coupled with a modem platform 530. The host platform 528 may include application processing circuitry 532 coupled with protocol processing circuitry 534 of the modem platform 530. The modem platform may further include digital baseband circuitry 536, transmit circuitry 538, receive circuitry 540, RF circuitry 542, RFFE circuitry 544, and antenna panels 546. The components of the AN 504 may be similar to and substantially interchangeable with like-named components of the UE 502. In addition to performing data transmission/reception as described above, the components of the AN 504 may perform various logical functions that include, for example, RNC functions such as radio bearer management, uplink and downlink dynamic radio resource management, and data packet scheduling. [0089] Fig. 6 is a block diagram illustrating components, according to some example embodiments, able to read instructions from a machine-readable or computer-readable medium (e.g., a non-transitory machine-readable storage medium) and perform any one or more of the methodologies discussed herein. Specifically, Fig. 6 shows a diagrammatic representation of hardware resources 600 including one or more processors (or processor cores) 610, one or more memory/storage devices 620, and one or more communication resources 630, each of which may be communicatively coupled via a bus 640 or other interface circuitry. For embodiments where node virtualization (e.g., NFV) is utilized, a hypervisor 602 may be executed to provide an execution environment for one or more network slices/sub-slices to utilize the hardware resources 600.

[0090] The processors 610 may include, for example, a processor 612 and a processor 614. The processors 610 may be, for example, a central processing unit (CPU), a reduced instruction set computing (RISC) processor, a complex instruction set computing (CISC) processor, a graphics processing unit (GPU), a DSP such as a baseband processor, an ASIC, an FPGA, a radiofrequency integrated circuit (RFIC), another processor (including those discussed herein), or any suitable combination thereof.

[0091] The memory/storage devices 620 may include main memory, disk storage, or any suitable combination thereof. The memory/storage devices 620 may include, but are not limited to, any type of volatile, non-volatile, or semi-volatile memory such as dynamic random access memory (DRAM), static random access memory (SRAM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), Flash memory, solid-state storage, etc.

[0092] The communication resources 630 may include interconnection or network interface controllers, components, or other suitable devices to communicate with one or more peripheral devices 604 or one or more databases 606 or other network elements via a network 608. For example, the communication resources 630 may include wired communication components (e.g., for coupling via USB, Ethernet, etc.), cellular communication components, NFC components, Bluetooth® (or Bluetooth® Low Energy) components, Wi-Fi® components, and other communication components.

[0093] Instructions 650 may comprise software, a program, an application, an applet, an app, or other executable code for causing at least any of the processors 610 to perform any one or more of the methodologies discussed herein. The instructions 650 may reside, completely or partially, within at least one of the processors 610 (e.g., within the processor’s cache memory), the memory/storage devices 620, or any suitable combination thereof. Furthermore, any portion of the instructions 650 may be transferred to the hardware resources 600 from any combination of the peripheral devices 604 or the databases 606. Accordingly, the memory of processors 610, the memory/storage devices 620, the peripheral devices 604, and the databases 606 are examples of computer-readable and machine-readable media.

[0094] Fig. 7 illustrates a simplified block diagram of artificial (Al)-assisted communication between a UE 705 and a RAN 710, in accordance with various embodiments. More specifically, as described in further detail below, Al/machine learning (ML) models may be used or leveraged to facilitate over-the-air communication between UE 705 and RAN 710.

[0095] One or both of the UE 705 and the RAN 710 may operate in a matter consistent with 3 GPP technical specifications or technical reports for 6G systems. In some embodiments, the wireless cellular communication between the UE 705 and the RAN 710 may be part of, or operate concurrently with, networks ZZX00, 400, and/or some other network described herein. [0096] The UE 705 may be similar to, and share one or more features with, UE ZZX02, UE 402, and/or some other UE described herein. The UE 705 may be, but is not limited to, a smartphone, tablet computer, wearable computer device, desktop computer, laptop computer, in-vehicle infotainment, in-car entertainment device, instrument cluster, head-up display device, onboard diagnostic device, dashtop mobile equipment, mobile data terminal, electronic engine management system, electronic/engine control unit, electronic/engine control module, embedded system, sensor, microcontroller, control module, engine management system, networked appliance, machine-type communication device, M2M or D2D device, loT device, etc. The RAN 710 may be similar to, and share one or more features with, RAN 414, RAN ZZX08, and/or some other RAN described herein.

[0097] As may be seen in Figure 7, the Al-related elements of UE 705 may be similar to the AI- related elements of RAN 710. For the sake of discussion herein, description of the various elements will be provided from the point of view of the UE 705, however it will be understood that such discussion or description will apply to equally named/numbered elements of RAN 710, unless explicitly stated otherwise. [0098] As previously noted, the UE 705 may include various elements or functions that are related to AI/ML. Such elements may be implemented as hardware, software, firmware, and/or some combination thereof. In embodiments, one or more of the elements may be implemented as part of the same hardware (e.g., chip or multi-processor chip), software (e.g., a computing program), or firmware as another element.

[0099] One such element may be a data repository 715. The data repository 715 may be responsible for data collection and storage. Specifically, the data repository 715 may collect and store RAN configuration parameters, measurement data, performance key performance indicators (KPIs), model performance metrics, etc., for model training, update, and inference. More generally, collected data is stored into the repository. Stored data can be discovered and extracted by other elements from the data repository 715. For example, as may be seen, the inference data sei ection/fi Iter element 750 may retrieve data from the data repository 715. In various embodiments, the UE 705 may be configured to discover and request data from the data repository 7154 in the RAN, and vice versa. More generally, the data repository 715 of the UE 705 may be communicatively coupled with the data repository 715 of the RAN 710 such that the respective data repositories of the UE and the RAN may share collected data with one another. [0100] Another such element may be a training data selection/filtering functional block 720. The training data selection/filter functional block 720 may be configured to generate training, validation, and testing datasets for model training. Training data may be extracted from the data repository 715. Data may be selected/filtered based on the specific AI/ML model to be trained. Data may optionally be transformed/augmented/pre-processed (e.g., normalized) before being loaded into datasets. The training data selection/filter functional block 720 may label data in datasets for supervised learning. The produced datasets may then be fed into model training the model training functional block 725.

[0101] As noted above, another such element may be the model training functional block 725. This functional block may be responsible for training and updating (re-training) AI/ML models. The selected model may be trained using the fed-in datasets (including training, validation, testing) from the training data selection/filtering functional block. The model training functional block 725 may produce trained and tested AI/ML models which are ready for deployment. The produced trained and tested models can be stored in a model repository 735. [0102] The model repository 735 may be responsible for AT/ML models’ (both trained and untrained) storage and exposure. Trained/updated model(s) may be stored into the model repository 735. Model and model parameters may be discovered and requested by other functional blocks (e.g., the training data selection/filter functional block 720 and/or the model training functional block 725). In some embodiments, the UE 705 may discover and request AI/ML models from the model repository 735 of the RAN 710. Similarly, the RAN 710 may be able to discover and/or request AI/ML models from the model repository 735 of the UE 705. In some embodiments, the RAN 710 may configure models and/or model parameters in the model repository 735 of the UE 705.

[0103] Another such element may be a model management functional block 740. The model management functional block 740 may be responsible for management of the AI/ML model produced by the model training functional block 725. Such management functions may include deployment of a trained model, monitoring model performance, etc. In model deployment, the model management functional block 740 may allocate and schedule hardware and/or software resources for inference, based on received trained and tested models. As used herein, “inference” refers to the process of using trained AI/ML model(s) to generate data analytics, actions, policies, etc. based on input inference data. In performance monitoring, based on wireless performance KPIs and model performance metrics, the model management functional block 740 may decide to terminate the running model, start model re-training, select another model, etc. In embodiments, the model management functional block 740 of the RAN 710 may be able to configure model management policies in the UE 705 as shown.

[0104] Another such element may be an inference data selection/filtering functional block 750. The inference data selection/filter functional block 750 may be responsible for generating datasets for model inference at the inference functional block 745, as described below. Specifically, inference data may be extracted from the data repository 715. The inference data selection/filter functional block 750 may select and/or filter the data based on the deployed AI/ML model. Data may be transformed/augmented/pre-processed following the same transformation/augmentation/pre-processing as those in training data selection/filtering as described with respect to functional block 720. The produced inference dataset may be fed into the inference functional block 745. [0105] Another such element may be the inference functional block 745. The inference functional block 745 may be responsible for executing inference as described above. Specifically, the inference functional block 745 may consume the inference dataset provided by the inference data selection/filtering functional block 750, and generate one or more outcomes. Such outcomes may be or include data analytics, actions, policies, etc. The outcome(s) may be provided to the performance measurement functional block 730.

[0106] The performance measurement functional block 730 may be configured to measure model performance metrics (e.g., accuracy, model bias, run-time latency, etc.) of deployed and executing models based on the inference outcome(s) for monitoring purpose. Model performance data may be stored in the data repository 715.

[0107] For one or more embodiments, at least one of the components set forth in one or more of the preceding figures may be configured to perform one or more operations, techniques, processes, and/or methods as set forth in the example section below. For example, the baseband circuitry as described above in connection with one or more of the preceding figures may be configured to operate in accordance with one or more of the examples set forth below. For another example, circuitry associated with a UE, base station, network element, etc. as described above in connection with one or more of the preceding figures may be configured to operate in accordance with one or more of the examples set forth below in the example section.

EXAMPLES

[0108] Example 1 includes a device to host a management service (MnS) producer for a wireless cellular network, the device including a memory to store instructions, and one or more processors coupled to the memory to execute the instructions to: receive, from an MnS consumer, a request to query information about one or more available machine learning (ML) emulation environments; and send to the MnS consumer one or more instances of an information object class (IOC) associated with respective ones of the one or more available emulation environments.

[0109] Example 2 includes the subject matter of Example 1, wherein the one or more instances of the IOC include information regarding supported features for the respective ones of the one or more available emulation environments. [0110] Example 3 includes the subject matter of any one of Examples 1-2, wherein the one or more instances of the IOC include information regarding a Third Generation Partnership Project release number.

[0111] Example 4 includes the subject matter of any one of Examples 1-3, wherein the one or more instances of the IOC includes information regarding a number of cells of the cellular network.

[0112] Example 5 includes the subject matter of any one of Examples 1-4, the one or more instances of the IOC include information regarding available resources for the respective ones of the one or more available emulation environments.

[0113] Example 6 includes the subject matter of Example 1, wherein the IOC is a first IOC, the one or more processors to execute the instructions to receive, from the MnS consumer, an instance of a second IOC, the instance of the second IOC corresponding to an emulation request including identification of a selected emulation environment of the one or more available emulation environments.

[0114] Example 7 includes the subject matter of Example 6, wherein the emulation request includes information regarding a request for an ML entity to perform an ML emulation in the selected emulation environment.

[0115] Example 8 includes the subject matter of Example 7, the one or more processors to execute the instructions to receive one or more attributes of an instance of a third IOC from the MnS consumer, the attributes corresponding to information regarding activation or deactivation of the ML entity during an emulation process corresponding to the ML emulation by the ML entity.

[0116] Example 9 includes the subject matter of Example 8, wherein any one of the activation or deactivation is of a type including: instant action, schedule based, policy based or gradual. [0117] Example 10 includes the subject matter of any one of Examples 7-9, therein the emulation request includes information regarding a time window for the ML emulation.

[0118] Example 11 includes the subject matter of Example 7, the one or more processors to execute the instructions to send to the MnS consumer an instance of a third IOC, the instance of the third IOC regarding indication of progress of an emulation process corresponding to the ML emulation by the ML entity. [0119] Example 12 includes the subject matter of Example 11 , the one or more processors to execute the instructions to send, to the MnS consumer, performance measurements related to the ML entity during the emulation process.

[0120] Example 13 includes the subject matter of Example 11, the one or more processors to send the instance of the third IOC to the MnS consumer during the emulation process.

[0121] Example 14 includes the subject matter of any one of Examples 11-13, wherein the instance of the third IOC includes information on a progress indicator for the emulation process. [0122] Example 15 includes the subject matter of any one of Examples 11-14, wherein the instance of the third IOC includes information on an identifier for the emulation request.

[0123] Example 16 includes the subject matter of any one of Examples 11-15, wherein the instance of the third IOC includes information on an attribute to control the emulation process. [0124] Example 17 includes the subject matter of Example 16, the one or more processors to execute the instructions to receive, from the MnS consumer, an instance of a fourth IOC, the instance of the fourth IOC including information to control the emulation process, controlling including starting, stopping, suspending, or resuming the emulation process.

[0125] Example 18 includes the subject matter of Example 17, wherein controlling further includes controlling the emulation process to be executed only within certain hours, or only on a particular set of cells.

[0126] Example 19 includes the subject matter of Example 1, wherein the MnS producer is implemented in a New Radio (NR) node B (gNodeB).

[0127] Example 20 includes the subject matter of Example 1, wherein the MnS producer is implemented in a management system separate from a gNodeB.

[0128] Example 21 includes a method to be performed at a management service (MnS) producer for a wireless cellular network, the method including: receiving, from an MnS consumer, a request to query information about one or more available machine learning (ML) emulation environments; and sending to the MnS consumer one or more instances of an information object class (IOC) associated with respective ones of the one or more available emulation environments.

[0129] Example 22 includes the subject matter of Example 21, wherein the one or more instances of the IOC include information regarding supported features for the respective ones of the one or more available emulation environments. [0130] Example 23 includes the subject matter of any one of Examples 21-22, wherein the one or more instances of the IOC include information regarding a Third Generation Partnership Project release number.

[0131] Example 24 includes the subject matter of any one of Examples 21-23, wherein the one or more instances of the IOC includes information regarding a number of cells of the cellular network.

[0132] Example 25 includes the subject matter of any one of Examples 21-24, the one or more instances of the IOC include information regarding available resources for the respective ones of the one or more available emulation environments.

[0133] Example 26 includes the subject matter of Example 21, wherein the IOC is a first IOC, further including receiving, from the MnS consumer, an instance of a second IOC, the instance of the second IOC corresponding to an emulation request including identification of a selected emulation environment of the one or more available emulation environments.

[0134] Example 27 includes the subject matter of Example 26, wherein the emulation request includes information regarding a request for an ML entity to perform an ML emulation in the selected emulation environment.

[0135] Example 28 includes the subject matter of Example 27, further including sending one or more attributes of an instance of a third IOC to the MnS producer, the one or more attributes corresponding to information regarding activation or deactivation of the ML entity during an emulation process corresponding to the ML emulation by the ML entity.

[0136] Example 29 includes the subject matter of Example 28, wherein any one of the activation or deactivation is of a type including: instant action, schedule based, policy based or gradual.

[0137] Example 30 includes the subject matter of any one of Examples 27-29, therein the emulation request includes information regarding a time window for the ML emulation.

[0138] Example 31 includes the subject matter of Example 27, further including sending to the MnS consumer an instance of a third IOC, the instance of the third IOC regarding indication of progress of an emulation process corresponding to the ML emulation by the ML entity.

[0139] Example 32 includes the subject matter of Example 31, further including sending, to the MnS consumer, performance measurements related to the ML entity during the emulation process. [0140] Example 33 includes the subject matter of Example 31 , further including sending the instance of the third IOC to the MnS consumer during the emulation process.

[0141] Example 34 includes the subject matter of any one of Examples 31-33, wherein the instance of the third IOC includes information on a progress indicator for the emulation process. [0142] Example 35 includes the subject matter of any one of Examples 31-34, wherein the instance of the third IOC includes information on an identifier for the emulation request.

[0143] Example 36 includes the subject matter of any one of Examples 31-35, wherein the instance of the third IOC includes information on an attribute to control the emulation process. [0144] Example 37 includes the subject matter of Example 35, further including receiving, from the MnS consumer, an instance of a fourth IOC, the instance of the fourth IOC including information to control the emulation process, controlling including starting, stopping, suspending, or resuming the emulation process.

[0145] Example 38 includes the subject matter of Example 36, wherein controlling further includes controlling the emulation process to be executed only within certain hours, or only on a particular set of cells.

[0146] Example 39 includes a device to host a management service (MnS) consumer in a wireless cellular network, the device including a memory to store instructions, and one or more processors coupled to the memory to execute the instructions to: send, to an MnS producer, a request to query information about one or more available machine learning (ML) emulation environments; and receive, from the MnS producer one or more instances of an information object class (IOC) associated with respective ones of the one or more available emulation environments.

[0147] Example 40 includes the subject matter of Example 39, wherein the one or more instances of the IOC include information regarding supported features for the respective ones of the one or more available emulation environments.

[0148] Example 41 includes the subject matter of any one of Examples 39-40, wherein the one or more instances of the IOC include information regarding a Third Generation Partnership Project release number.

[0149] Example 42 includes the subject matter of any one of Examples 39-41, wherein the one or more instances of the IOC includes information regarding a number of cells of the cellular network. [0150] Example 43 includes the subject matter of any one of Examples 39-42, the one or more instances of the IOC include information regarding available resources for the respective ones of the one or more available emulation environments.

[0151] Example 44 includes the subject matter of Example 39, wherein the IOC is a first IOC, the one or more processors to execute the instructions to send, to the MnS producer, an instance of a second IOC, the instance of the second IOC corresponding to an emulation request including identification of a selected emulation environment of the one or more available emulation environments.

[0152] Example 45 includes the subject matter of Example 44, wherein the emulation request includes information regarding a request for an ML entity to perform an ML emulation in the selected emulation environment.

[0153] Example 46 includes the subject matter of Example 45, the one or more processors to execute the instructions to send one or more attributes of an instance of a third IOC to the MnS producer, the one or more attributes corresponding to information regarding activation or deactivation of the ML entity during an emulation process corresponding to the ML emulation by the ML entity.

[0154] Example 47 includes the subject matter of Example 46, wherein any one of the activation or deactivation is of a type including: instant action, schedule based, policy based or gradual. [0155] Example 48 includes the subject matter of any one of Examples 45-47, therein the emulation request includes information regarding a time window for the ML emulation.

[0156] Example 49 includes the subject matter of Example 45, the one or more processors to execute the instructions to receive from the MnS producer an instance of a third IOC, the instance of the third IOC regarding indication of progress of an emulation process corresponding to the ML emulation by the ML entity.

[0157] Example 50 includes the subject matter of Example 49, the one or more processors to execute the instructions to receive, from the MnS producer, performance measurements related to the ML entity during the emulation process.

[0158] Example 51 includes the subject matter of Example 49, the one or more processors to receive the instance of the third IOC from the MnS producer during the emulation process. [0159] Example 52 includes the subject matter of any one of Examples 49-51, wherein the instance of the third IOC includes information on a progress indicator for the emulation process. [0160] Example 53 includes the subject matter of any one of Examples 49-52, wherein the instance of the third IOC includes information on an identifier for the emulation request.

[0161] Example 54 includes the subject matter of any one of Examples 49-53, wherein the instance of the third IOC includes information on an attribute to control the emulation process. [0162] Example 55 includes the subject matter of Example 54, the one or more processors to execute the instructions to receive, from the MnS producer, an instance of a fourth IOC, the instance of the fourth IOC including information to control the emulation process, controlling including starting, stopping, suspending, or resuming the emulation process.

[0163] Example 56 includes the subject matter of Example 55, wherein controlling further includes controlling the emulation process to be executed only within certain hours, or only on a particular set of cells.

[0164] Example 57 includes the subject matter of Example 39, wherein the MnS consumer is implemented in a New Radio (NR) node B (gNodeB).

[0165] Example 58 includes the subject matter of Example 39, wherein the MnS producer is implemented in a server.

[0166] Example 59 includes a method to be performed at a management service (MnS) consumer in a wireless cellular network: send, to an MnS producer, a request to query information about one or more available machine learning (ML) emulation environments; and receive, from the MnS producer one or more instances of an information object class (IOC) associated with respective ones of the one or more available emulation environments.

[0167] Example 60 includes the subject matter of Example 59, wherein the one or more instances of the IOC include information regarding supported features for the respective ones of the one or more available emulation environments.

[0168] Example 61 includes the subject matter of any one of Examples 59-60, wherein the one or more instances of the IOC include information regarding a Third Generation Partnership Project release number.

[0169] Example 62 includes the subject matter of any one of Examples 59-61, wherein the one or more instances of the IOC includes information regarding a number of cells of the cellular network. [0170] Example 63 includes the subject matter of any one of Examples 59-62, the one or more instances of the IOC include information regarding available resources for the respective ones of the one or more available emulation environments.

[0171] Example 64 includes the subject matter of Example 59, wherein the IOC is a first IOC, further including sending, to the MnS producer, an instance of a second IOC, the instance of the second IOC corresponding to an emulation request including identification of a selected emulation environment of the one or more available emulation environments.

[0172] Example 65 includes the subject matter of Example 64, wherein the emulation request includes information regarding a request for an ML entity to perform an ML emulation in the selected emulation environment.

[0173] Example 66 includes the subject matter of Example 65, further including sending one or more attributes of an instance of a third IOC to the MnS producer, the one or more attributes corresponding to information regarding activation or deactivation of the ML entity during an emulation process corresponding to the ML emulation by the ML entity.

[0174] Example 67 includes the subject matter of Example 66, wherein any one of the activation or deactivation is of a type including: instant action, schedule based, policy based or gradual.

[0175] Example 68 includes the subject matter of any one of Examples 65-67, therein the emulation request includes information regarding a time window for the ML emulation.

[0176] Example 69 includes the subject matter of Example 65, further including receiving from the MnS producer an instance of a third IOC, the instance of the third IOC regarding indication of progress of an emulation process corresponding to the ML emulation by the ML entity.

[0177] Example 70 includes the subject matter of Example 69, further including receiving, from the MnS producer, performance measurements related to the ML entity during the emulation process.

[0178] Example 71 includes the subject matter of Example 69, further including receiving the instance of the third IOC from the MnS producer during the emulation process.

[0179] Example 72 includes the subject matter of any one of Examples 69-71, wherein the instance of the third IOC includes information on a progress indicator for the emulation process. [0180] Example 73 includes the subject matter of any one of Examples 59-72, wherein the instance of the third IOC includes information on an identifier for the emulation request. [0181] Example 74 includes the subject matter of any one of Examples 59-73, wherein the instance of the third IOC includes information on an attribute to control the emulation process. [0182] Example 75 includes the subject matter of Example 74, further including receiving, from the MnS producer, an instance of a fourth IOC, the instance of the fourth IOC including information to control the emulation process, controlling including starting, stopping, suspending, or resuming the emulation process.

[0183] Example 76 includes the subject matter of Example 75, wherein controlling further includes controlling the emulation process to be executed only within certain hours, or only on a particular set of cells.

[0184] Example 77 includes one or more computer-readable media comprising instructions that, when executed by one or more processors, cause the one or more processors to perform the method of any one of claims 21-38 or 59-76.

[0185] Example 78 includes means for performing the method of any one of claims 21-38 or 59- 76.

[0186] Example Al may include a method wherein a service producer supported by one or more processors is configured to: receive a request from a consumer for querying the information about the available emulation environments; provide information about the available emulation environments to a consumer.

[0187] Example A2 may include the method according to example 1 or some other example herein, wherein the service producer is further configured to: receive a request from a consumer to run the emulation for an ML entity; provide the response to the consumer to indicate whether the request is accepted; start the emulation process; report the progress of the emulation.

[0188] Example A3 may include the method according to example 1 or some other example herein, wherein the information about the available emulation environments is provided by the instance(s) of the IOC (Information Object class) representing the available emulation environment.

[0189] Example A4 may include the method according to example 2 or some other example herein, wherein the emulation request is provided by the instance(s) of the IOC (Information Object class) representing the emulation request. [0190] Example A5 may include the method according to example 2 or some other example herein, wherein the emulation process is provided by the instance(s) of the IOC (Information Object class) representing the emulation process.

[0191] Example A6 may include the method according to example 3 or some other example herein, wherein the IOC (Information Object class) representing the available emulation environment contains at least one of the following attributes: description of the environment, such as supported features, corresponding 3GPP release number, number of cells, etc., the available resources (processing resources, memory resources, etc.

[0192] Example A7 may include the method according to example 4 or some other example herein, wherein the IOC (Information Object class) representing the emulation request contains at least one of the following attributes: identifier of the ML entities requested for emulation, identifier of the selected emulation environment, time window for the emulation.

[0193] Example A8 may include the method according to example 5 or some other example herein, wherein the IOC (Information Object class) representing the emulation process contains at least one of the following attributes: progress indicator, the identifier of the corresponding emulation request, attribute for controlling the process, such as starting, stopping, suspending, and resuming.

[0194] Example A9 may include the method according to example 1 or some other example herein, wherein the service producer is further configured to: receive a request from a consumer to activate or deactivate an ML entity during the emulation; provide the response to the consumer to indicate whether the request is accepted; activate or deactivate the ML entity accordingly during the emulation.

[0195] Example A10 may include the method according to example 9 or some other example herein, wherein the activation or deactivation is one of the following types: instant action, schedule based, policy based, gradual activation or deactivation.

[0196] Example Al 1 may include the method according to examples 9 and 10 or some other example herein, wherein the activation or deactivation request is provided by one or more attributes of an instance of IOC.

[0197] Example A12 may include the method according to example 1 or some other example herein, wherein the service producer is further configured to: provide the inference report(s) of the ML entity during the emulation to the consumer; provide the performance measurements related to the ML entity during the emulation to the consumer.

[0198] Example A13 may include a method of a service producer for a wireless cellular network, the method comprising:

[0199] receiving, from a service consumer, a request for information associated with available emulation environments; sending the information associated with the available emulation environments to the service consumer.

[0200] Example A14 may include the method according to example 13 or some other example herein, further comprising: receiving, from the service consumer, a request to run an emulation for a machine learning (ML) entity using a first emulation environment of the available emulation environments; running the requested emulation; and reporting progress and/or results of the emulation.

[0201] Example A15 may include the method according to example 13-14 or some other example herein, wherein the information associated with the available emulation environments includes one or more information object class (IOC) instances associated with respective available emulation environments.

[0202] Example Al 6 may include the method according to example 15 or some other example herein, wherein the IOC includes one or more of: a description of the emulation environment (e.g., such as supported features, corresponding 3GPP release number, number of cells, etc.); and/or available resources for the emulation environment (e.g., processing resources, memory resources, etc.).

[0203] Example Z01 may include an apparatus comprising means to perform one or more elements of a method described in or related to any of examples 1-16, or any other method or process described herein.

[0204] Example Z02 may include one or more non-transitory computer-readable media comprising instructions to cause an electronic device, upon execution of the instructions by one or more processors of the electronic device, to perform one or more elements of a method described in or related to any of examples 1-16, or any other method or process described herein. [0205] Example Z03 may include an apparatus comprising logic, modules, or circuitry to perform one or more elements of a method described in or related to any of examples 1-16, or any other method or process described herein. [0206] Example Z04 may include a method, technique, or process as described in or related to any of examples 1-16, or portions or parts thereof.

[0207] Example Z05 may include an apparatus comprising: one or more processors and one or more computer-readable media comprising instructions that, when executed by the one or more processors, cause the one or more processors to perform the method, techniques, or process as described in or related to any of examples 1-16, or portions thereof.

[0208] Example Z06 may include a signal as described in or related to any of examples 1-16, or portions or parts thereof.

[0209] Example Z07 may include a datagram, packet, frame, segment, protocol data unit (PDU), or message as described in or related to any of examples 1-16, or portions or parts thereof, or otherwise described in the present disclosure.

[0210] Example Z08 may include a signal encoded with data as described in or related to any of examples 1-16, or portions or parts thereof, or otherwise described in the present disclosure.

[0211] Example Z09 may include a signal encoded with a datagram, packet, frame, segment, protocol data unit (PDU), or message as described in or related to any of examples 1-16, or portions or parts thereof, or otherwise described in the present disclosure.

[0212] Example Z10 may include an electromagnetic signal carrying computer-readable instructions, wherein execution of the computer-readable instructions by one or more processors is to cause the one or more processors to perform the method, techniques, or process as described in or related to any of examples 1-16, or portions thereof.

[0213] Example Z11 may include a computer program comprising instructions, wherein execution of the program by a processing element is to cause the processing element to carry out the method, techniques, or process as described in or related to any of examples 1-16, or portions thereof.

[0214] Example Z 12 may include a signal in a wireless network as shown and described herein.

[0215] Example Z13 may include a method of communicating in a wireless network as shown and described herein.

[0216] Example Z 14 may include a system for providing wireless communication as shown and described herein.

[0217] Example Z15 may include a device for providing wireless communication as shown and described herein. [0218] Any of the above-described examples may be combined with any other example (or combination of examples), unless explicitly stated otherwise. The foregoing description of one or more implementations provides illustration and description, but is not intended to be exhaustive or to limit the scope of embodiments to the precise form disclosed. Modifications and variations are possible in light of the above teachings or may be acquired from practice of various embodiments.

Claims

What is Claimed Is:

1. A device to host a management service (MnS) producer for a wireless cellular network, the device including a memory to store instructions, and one or more processors coupled to the memory to execute the instructions to: receive, from an MnS consumer, a request to query information about one or more available machine learning (ML) emulation environments; and send to the MnS consumer one or more instances of an information object class (IOC) associated with respective ones of the one or more available emulation environments.

2. The device of claim 1, wherein the one or more instances of the IOC include information regarding supported features for the respective ones of the one or more available emulation environments.

3. The device of claim 1, wherein the one or more instances of the IOC includes information regarding a number of cells of the cellular network.

4. The device of any one of claims 1-3, the one or more instances of the IOC include information regarding available resources for the respective ones of the one or more available emulation environments.

5. The device of claim 1, wherein the IOC is a first IOC, the one or more processors to execute the instructions to receive, from the MnS consumer, an instance of a second IOC, the instance of the second IOC corresponding to an emulation request including identification of a selected emulation environment of the one or more available emulation environments.

6. The device of claim 5, wherein the emulation request includes information regarding a request for an ML entity to perform an ML emulation in the selected emulation environment.

7. The device of claim 6, the one or more processors to execute the instructions to send to the MnS consumer an instance of a third IOC, the instance of the third IOC regarding indication of progress of an emulation process corresponding to the ML emulation by the ML entity.

8. The device of claim 6, the one or more processors to execute the instructions to receive one or more attributes of an instance of a third IOC from the MnS consumer, the one or more attributes corresponding to information regarding activation or deactivation of the ML entity during an emulation process corresponding to the ML emulation by the ML entity.

9. The device of claim 8, wherein any one of the activation or deactivation is of a type including: instant action, schedule based, policy based or gradual.

10. The device of claim 7, the one or more processors to execute the instructions to send, to the MnS consumer during the emulation process, performance measurements related to the ML entity during the emulation process.

11. The device of any one of claims 7-10, wherein the instance of the third IOC includes information on at least one of a progress indicator for the emulation process, an identifier for the emulation request, or an attribute to control the emulation process.

12. The device of claim 11, the one or more processors to execute the instructions to receive, from the MnS consumer, one or more attributes for an instance of a third IOC, one or more attributes the one or more attributes the one or more attributes including information to control the emulation process, controlling including starting, stopping, suspending, or resuming the emulation process.

13. The device of any one of claims 1-3 and 5-10, wherein the MnS producer is implemented in one of a New Radio (NR) node B (gNodeB) or a management system separate from a gNodeB.

14. A method to be performed at a management service (MnS) consumer in a wireless cellular network, the method including: sending, to an MnS producer, a request to query information about one or more available machine learning (ML) emulation environments; and receiving, from the MnS producer one or more instances of an information object class (IOC) associated with respective ones of the one or more available emulation environments.

15. The method of claim 14, wherein the one or more instances of the IOC include information regarding supported features for the respective ones of the one or more available emulation environments.

16. The method of claim 14, the one or more instances of the IOC include information regarding available resources for the respective ones of the one or more available emulation environments.

17. The method of claim 14, wherein the IOC is a first IOC, further including sending, to the MnS producer, an instance of a second IOC, the instance of the second IOC corresponding to an emulation request including identification of a selected emulation environment of the one or more available emulation environments.

18. The method of claim 17, wherein the emulation request includes information regarding a request for an ML entity to perform an ML emulation in the selected emulation environment.

19. The method of claim 18, further including receiving from the MnS producer an instance of a third IOC, the instance of the third IOC regarding indication of progress of an emulation process corresponding to the ML emulation by the ML entity.

20. The method of claim 18, further including sending one or more attributes of an instance of a third IOC to the MnS producer, the one or more attributes corresponding to information regarding activation or deactivation of the ML entity during an emulation process corresponding to the ML emulation by the ML entity.

21. The method of claim 19, further including receiving, from the MnS producer, during the emulation process, performance measurements related to the ML entity during the emulation process.

22. The method of claim 20, further including sending, to the MnS producer, one or more attributes of an instance of a third IOC, the one or more attributes including information to control the emulation process, controlling including starting, stopping, suspending, or resuming the emulation process.

23. The method of claim 22, wherein controlling further includes controlling the emulation process to be executed only within certain hours, or only on a particular set of cells.

24. A device including means to perform the method of any one of claims 14-23.

25. One or more computer-readable media comprising instructions that, when executed by one or more processors, cause the one or more processors to perform the method of any one of claims 14-23.