WO2024088572A1

WO2024088572A1 - Registering and discovering external federated learning clients in a wireless communication system

Info

Publication number: WO2024088572A1
Application number: PCT/EP2023/054215
Authority: WO
Inventors: Emmanouil Pateromichelakis; Konstantinos Samdanis; Dimitrios Karampatsis
Original assignee: Lenovo (Singapore) Pte. Ltd.
Priority date: 2023-01-05
Filing date: 2023-02-20
Publication date: 2024-05-02

Abstract

There is provided an application entity in a wireless communication system, comprising: a processor; and a memory coupled with the processor. The processor is configured to cause the application entity to: receive, from at least one other network or application entity of a wireless communication system, a query for acting as a federated learning participant for a particular machine learning enabled analytics event, wherein the wireless communication system comprises a core network; determine, for the particular machine learning enabled analytics event, a federated learning client profile, wherein the federated learning client profile comprises a capability of the application entity to act as a federated learning client for at least one data source that is external to the core network, and/or to act as a data source that is external to the core network, for the particular machine learning enabled analytics event; and transmit, to a service registry entity, a request for registering a registration information, the registration information comprising the federated learning client profile and an identifier for the application entity.

Description

REGISTERING AND DISCOVERING EXTERNAL

FEDERATED LEARNING CLIENTS IN A

WIRELESS COMMUNICATION SYSTEM

Field

[0001] The subject matter disclosed herein relates generally to the field of implementing the registering and discovering of federated learning clients in a wireless communication system. This document defines an application entity, a server entity, and a service registry entity, in a wireless communication system. This document also defines methods in an application entity, server entity and service registry entity, in a wireless communication system.

Introduction

[0002] In the third-generation partnership project (3GPP), fifth generation (5G) core analytics services are provided by the network data analytics function (NWDAF). This is described in 3GPP specification TS 23.288. Such analytics can collect data from other network functions (NF), or application functions (AF) or operations and maintenance (OAM) and can be exposed to other NFs, OAM and even 3rd party/ AF to provide statistics and predictions related to, e.g., slice Load level, observed Service experience, NF Load, Network Performance, user equipment (UE) related analytics (mobility, communication), User data congestion, quality of service (QoS) sustainability, data network (DN) performance, etc. Moreover, in 3GPP SA5 (TS 28.104), management data analytics (MDA) provides data analytics for the network management. MDA can be deployed at different levels, for example, network element level, e.g., gNodeB, at domain level (e.g., radio access network (RAN), core network (CN), network slice subnet) or in a centralized manner (e.g., in a public land mobile network (PLMN) level). The objective of MDA is to provide root case analysis on complex problems and optimize the network resource allocation (e.g., in network / domain level, in slice / slice subnet level).

[0003] An additional analytics function in 3GPP is discussed in 3GPP SA6 (TS 23.436), where an application data analytics enablement service (AD AES) is defined for performing app layer and edge / cloud analytics outside the 3GPP domain. AD AES can be realized an AF, which has analytics capability, and also has an interface to the UE side (to ADAE client) as well as to the OAM. [0004] AD AES supports analytics (e.g., vertical application layer (VAL) server performance, edge load analytics, location analytics etc.), which can be machine learning (ML) -enabled. There are different deployments and business models for AD AES supported in TS 23.436. For example, AD AES can be within PLMN, or at an edge computing service provider (ECSP) (e.g., AWS) or at vertical domain (e.g., BMW). Regarding the deployment models, there are three possible scenarios (centralized, distributed, coordinated).

Summary

[0005] One key scenario in ML-enabled analytics is the federation learning support, as part of NWDAF. In particular, for ML-enabled analytics, TR 23.700-81 is investigating enhancements to support federated learning within the 5G system. The main functions of the federated learning (FL) architecture include: an ‘FL Consumer’ NWDAF as either an NWDAF containing a analytics logical function (AnLF), or an NWDAF containing a model training logical function (MTLF) for a specific Analytics ID; an ‘FL Server’ NWDAF as an NWDAF containing MTLF that supports the "FL aggregation" capability for the specific Analytics ID; and an ‘FL Client’ NWDAF as an NWDAF containing MTLF that supports the "FL participant" capability for the specific Analytics ID and selected by the "FL Server" NWDAF as the FL Client.

[0006] The current assumption is that the FL clients are within the core network (NFs, NWDAF); however, it would be beneficial to also consider FL clients belonging to different domains or systems /platforms. By way of example, an FL client could be an AF or a UE (behind an AF, or UE supporting a subscriber-aware northbound API access (SNA)). As a further example, an FL client could be a service enabler architecture layer (SEAL) /AD AE server (defined in 3GPP SA6) or a vertical app. As an additional example, an FL client could be a multiaccess edge computing (MEC) service or MEC app (for example RNI service can be enhanced to act as FL client).

[0007] Currently, in 3GPP SA2, the MTLF determines FL is needed based on the a number of conditions. These include, data not being available from a data source (due to privacy issues); target area; and pre-configuration based on analytic ID of the model requested by an AnLF.

[0008] The benefit for having cross-domain FL clients and in particular FL client at application side could offload some processing and communications for FL training from 5GC especially in high load scenarios. Furthermore it could allow FL training with more granular data (e.g., vertical application layer, edge/ cloud data) which can give better predictions. Furthermore it could allow training on different training data or different areas, which could allow aggregation over different environments (could also help improving analytics performance). In addition is may allow the training of data co-located with the data sources which can improve the latency and also avoid sending training data to different domains (maybe there are some restrictions on sharing raw data e.g. from vertical to mobile network operator (MNO)). The latter is a main motivation, since it is not certain that a Data Producer outside core network would be willing to send raw data to be trained at MNO domain, and it would be preferable that the model is trained at the data producer domain.

[0009] Based on these considerations, a heterogeneous set of FL clients, i.e., vertical FL, is expected, and enhancements are needed to determine how discovery / selection of FL clients happens, and how ML models are distributed.

[0010] Disclosed herein are procedures for registering and discovering external federated learning clients in a wireless communication system. Said procedures may be implemented by an application entity, a server entity and a service registry entity, in a wireless communication system.

[0011] There is provided an application entity in a wireless communication system, comprising a processor; and a memory coupled with the processor, the processor configured to cause the application entity to: receive, from at least one other network or application entity of a wireless communication system, a query for acting as a federated learning participant for a particular machine learning enabled analytics event, wherein the wireless communication system comprises a core network; determine, for the particular machine learning enabled analytics event, a federated learning client profile, wherein the federated learning client profile comprises a capability of the application entity to act as a federated learning client for at least one data source that is external to the core network, and/ or to act as a data source that is external to the core network, for the particular machine learning enabled analytics event; and transmit, to a service registry entity, a request for registering a registration information, the registration information comprising the federated learning client profile and an identifier for the application entity.

[0012] There is further provided, a server entity in a wireless communication system, comprising a processor; and a memory coupled with the processor, the processor configured to cause the server entity to: determine a federated learning requirement for a particular machine learning enabled analytics event, wherein the federated learning requirement uses at least one application entity that is external to a core network of the wireless communication system; and transmit, to a service registry entity, a request to discover information of the at least one application entity, based on the federated learning requirement.

[0013] There is further provided, a service registry entity in a wireless communication system, comprising: a processor; and a memory coupled with the processor, the processor configured to cause the service registry entity to: receive, from at least one application entity external to a core network of the wireless communication system, a request for registering a registration information, the registration information comprising an identity of the respective application entity and a respective federated learning client profile, wherein the federated learning client profile comprises a capability of the respective application entity to act as a federated learning client for at least one data source that is external to the core network and/ or to act as a data source that is external to the core network, for a particular machine learning enabled analytics event; and store, in the memory, the registration information.

[0014] Furthermore, there is provided a method in an application entity, the application entity in a wireless communication system, comprising: receiving, from at least one other network or application entity of the wireless communication system, a query for acting as a federated learning participant for a particular machine learning enabled analytics event, wherein the wireless communication system comprises a core mobile network; determining, for the particular machine learning enabled analytics event, a federated learning client profile, wherein the federated learning client profile comprises a capability of the application entity to act as a federated learning client for at least one data source that is external to the core network and/ or to act as a data source that is external to the core network, for the particular machine learning enabled analytics event; and transmitting, to a service registry entity, a request for registering a registration information, the registration information comprising the federated learning client profile and an identifier for the application entity.

[0015] There is further provided, a method in a server entity, the server entity in a wireless communication system, comprising determining a federated learning requirement for a particular machine learning enabled analytics event, wherein the federated learning requirement uses at least one application entity that is external to a core network of the wireless communication system; and transmitting, to a service registry entity, a request to discover information of the at least one application entity, based on the federated learning requirement.

[0016] There is further provided, a method in a service registry entity, the service registry entity in a wireless communication system, comprising receiving, from at least one application entity external to a core network of the wireless communication system, a request for registering a registration information, the registration information comprising an identity of the respective application entity and a respective federated learning client profile, wherein the federated learning client profile comprises a capability of the respective application entity to act as a federated learning client for at least one data source that is external to the core network and/ or to act as a data source that is external to the core network, for a particular machine learning enabled analytics event; and storing the registration information.

Brief description of the drawings

[0017] In order to describe the manner in which advantages and features of the disclosure can be obtained, a description of the disclosure is rendered by reference to certain apparatus and methods which are illustrated in the appended drawings. Each of these drawings depict only certain aspects of the disclosure and are not therefore to be considered to be limiting of its scope. The drawings may have been simplified for clarity and are not necessarily drawn to scale.

[0018] Methods and apparatus for registering and discovering external federated learning clients in a wireless communication system will now be described, by way of example only, with reference to the accompanying drawings, in which:

Figure 1 illustrates an embodiment of a wireless communication system;

Figure 2 illustrates an embodiment of a user equipment apparatus;

Figure 3 illustrates an embodiment of a network node or network entity;

Figure 4 illustrates an embodiment of a high-level SEAT ADAE architecture; Figure 5 illustrates an embodiment of a coordinated AD AES deployment model; Figure 6 illustrates an embodiment of ML federated learning being deployed; Figure 7 illustrates an embodiment of a method in an application entity, in a wireless communication system;

Figure 8 illustrates an embodiment of a method in a server entity, in a wireless communication system; Figure 9 illustrates an embodiment of a method in a service registry, in a wireless communication system;

Figure 10 illustrates an embodiment of a method in an exposure function, in a wireless communication system;

Figure 11 illustrates an embodiment of registration and discovery via an NRF for a trusted AF; and

Figure 12 illustrates an embodiment of registration and discovery for an untrusted AF/UE.

Detailed description

[0019] As will be appreciated by one skilled in the art, aspects of this disclosure may be embodied as a system, apparatus, method, or program product. Accordingly, arrangements described herein may be implemented in an entirely hardware form, an entirely software form (including firmware, resident software, micro-code, etc.) or a form combining software and hardware aspects.

[0020] For example, the disclosed methods and apparatus may be implemented as a hardware circuit comprising custom very-large-scale integration (“VLSI”) circuits or gate arrays, off-the-shelf semiconductors such as logic chips, transistors, or other discrete components. The disclosed methods and apparatus may also be implemented in programmable hardware devices such as field programmable gate arrays, programmable array logic, programmable logic devices, or the like. As another example, the disclosed methods and apparatus may include one or more physical or logical blocks of executable code which may, for instance, be organized as an object, procedure, or function.

[0021] Furthermore, the methods and apparatus may take the form of a program product embodied in one or more computer readable storage devices storing machine readable code, computer readable code, and/ or program code, referred hereafter as code. The storage devices may be tangible, non-transitory, and/ or non-transmission. The storage devices may not embody signals. In certain arrangements, the storage devices only employ signals for accessing code.

[0022] Any combination of one or more computer readable medium may be utilized. The computer readable medium may be a computer readable storage medium. The computer readable storage medium may be a storage device storing the code. The storage device may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, holographic, micromechanical, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing.

[0023] More specific examples (a non-exhaustive list) of the storage device would include the following: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random-access memory (“RAM”), a read-only memory (“ROM”), an erasable programmable read-only memory (“EPROM” or Flash memory), a portable compact disc read-only memory (“CD-ROM”), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this document, a computer readable storage medium may be any tangible medium that can contain, or store, a program for use by or in connection with an instruction execution system, apparatus, or device.

[0024] Reference throughout this specification to an example of a particular method or apparatus, or similar language, means that a particular feature, structure, or characteristic described in connection with that example is included in at least one implementation of the method and apparatus described herein. Thus, reference to features of an example of a particular method or apparatus, or similar language, may, but do not necessarily, all refer to the same example, but mean “one or more but not all examples” unless expressly specified otherwise. The terms “including”, “comprising”, “having”, and variations thereof, mean “including but not limited to”, unless expressly specified otherwise. An enumerated listing of items does not imply that any or all of the items are mutually exclusive, unless expressly specified otherwise. The terms “a”, “an”, and “the” also refer to “one or more”, unless expressly specified otherwise.

[0025] As used herein, a list with a conjunction of “and/ or” includes any single item in the list or a combination of items in the list. For example, a list of A, B and/ or C includes only A, only B, only C, a combination of A and B, a combination of B and C, a combination of A and C or a combination of A, B and C. As used herein, a list using the terminology “one or more of’ includes any single item in the list or a combination of items in the list. For example, one or more of A, B and C includes only A, only B, only C, a combination of A and B, a combination of B and C, a combination of A and C or a combination of A, B and C. As used herein, a list using the terminology “one of’ includes one, and only one, of any single item in the list. For example, “one of A, B and C” includes only A, only B or only C and excludes combinations of A, B and C. As used herein, “a member selected from the group consisting of A, B, and C” includes one and only one of A, B, or C, and excludes combinations of A, B, and C.” As used herein, “a member selected from the group consisting of A, B, and C and combinations thereof’ includes only A, only B, only C, a combination of A and B, a combination of B and C, a combination of A and C or a combination of A, B and C.

[0026] Furthermore, the described features, structures, or characteristics described herein may be combined in any suitable manner. In the following description, numerous specific details are provided, such as examples of programming, software modules, user selections, network transactions, database queries, database structures, hardware modules, hardware circuits, hardware chips, etc., to provide a thorough understanding of the disclosure. One skilled in the relevant art will recognize, however, that the disclosed methods and apparatus may be practiced without one or more of the specific details, or with other methods, components, materials, and so forth. In other instances, well- known structures, materials, or operations are not shown or described in detail to avoid obscuring aspects of the disclosure.

[0027] Aspects of the disclosed method and apparatus are described below with reference to schematic flowchart diagrams and/or schematic block diagrams of methods, apparatuses, systems, and program products. It will be understood that each block of the schematic flowchart diagrams and/ or schematic block diagrams, and combinations of blocks in the schematic flowchart diagrams and/or schematic block diagrams, can be implemented by code. This code may be provided to a processor of a general-purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions /acts specified in the schematic flowchart diagrams and/or schematic block diagrams.

[0028] The code may also be stored in a storage device that can direct a computer, other programmable data processing apparatus, or other devices to function in a particular manner, such that the instructions stored in the storage device produce an article of manufacture including instructions which implement the function/ act specified in the schematic flowchart diagrams and/or schematic block diagrams.

[0029] The code may also be loaded onto a computer, other programmable data processing apparatus, or other devices to cause a series of operational steps to be performed on the computer, other programmable apparatus, or other devices to produce a computer implemented process such that the code which executes on the computer or other programmable apparatus provides processes for implementing the functions /acts specified in the schematic flowchart diagrams and/ or schematic block diagram.

[0030] The schematic flowchart diagrams and/ or schematic block diagrams in the Figures illustrate the architecture, functionality, and operation of possible implementations of apparatuses, systems, methods, and program products. In this regard, each block in the schematic flowchart diagrams and/or schematic block diagrams may represent a module, segment, or portion of code, which includes one or more executable instructions of the code for implementing the specified logical function(s). [0031] It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the Figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. Other steps and methods may be conceived that are equivalent in function, logic, or effect to one or more blocks, or portions thereof, of the illustrated Figures.

[0032] The description of elements in each figure may refer to elements of proceeding Figures. Like numbers refer to like elements in all Figures.

[0033] Figure 1 depicts an embodiment of a wireless communication system 100 for registering and discovering external federated learning clients. Such a system 100 may comprise the application entities within the trusted domain of the mobile network. Such a system 100 may comprise a core network or core mobile network. In one embodiment, the wireless communication system 100 includes remote units 102 and network units 104. Even though a specific number of remote units 102 and network units 104 are depicted in Figure 1, one of skill in the art will recognize that any number of remote units 102 and network units 104 may be included in the wireless communication system 100. [0034] In one embodiment, the remote units 102 may include computing devices, such as desktop computers, laptop computers, personal digital assistants (“PDAs”), tablet computers, smart phones, smart televisions (e.g., televisions connected to the Internet), set-top boxes, game consoles, security systems (including security cameras), vehicle onboard computers, network devices (e.g., routers, switches, modems), aerial vehicles, drones, or the like. In some embodiments, the remote units 102 include wearable devices, such as smartwatches, fitness bands, optical head-mounted displays, or the like. Moreover, the remote units 102 may be referred to as subscriber units, mobiles, mobile stations, users, terminals, mobile terminals, fixed terminals, subscriber stations, UE, user terminals, a device, or by other terminology used in the art. The remote units 102 may communicate directly with one or more of the network units 104 via UL communication signals. In certain embodiments, the remote units 102 may communicate directly with other remote units 102 via sidelink communication.

[0035] The network units 104 may be distributed over a geographic region. In certain embodiments, a network unit 104 may also be referred to as an access point, an access terminal, a base, a base station, a Node-B, an eNB, a gNB, a Home Node-B, a relay node, a device, a core network, an aerial server, a radio access node, an AT, NR, a network entity, an Access and Mobility Management Function (“AMF”), a Unified Data Management Function (“UDM”), a Unified Data Repository (“UDR”), a UDM/UDR, a Policy Control Function (“PCF”), a Radio Access Network (“RAN”), an Network Slice Selection Function (“NSSF”), an operations, administration, and management (“OAM”), a session management function (“SMF”), a user plane function (“UPF”), an application function, an authentication server function (“AUSF”), security anchor functionality (“SEAF”), trusted non-3GPP gateway function (“TNGF”), an application function, a service enabler architecture layer (“SEAL”) function, a vertical application enabler server, an edge enabler server, an edge configuration server, a mobile edge computing platform function, a mobile edge computing application, an application data analytics enabler server, a SEAL data delivery server, a middleware entity, a network slice capability management server, or by any other terminology used in the art. The network units 104 are generally part of a radio access network that includes one or more controllers communicab ly coupled to one or more corresponding network units 104. The radio access network is generally communicably coupled to one or more core networks, which may be coupled to other networks, like the Internet and public switched telephone networks, among other networks. These and other elements of radio access and core networks are not illustrated but are well known generally by those having ordinary skill in the art.

[0036] In one implementation, the wireless communication system 100 is compliant with New Radio (NR) protocols standardized in 3GPP, wherein the network unit 104 transmits using an Orthogonal Frequency Division Multiplexing (“OFDM”) modulation scheme on the downlink (DL) and the remote units 102 transmit on the uplink (UL) using a Single Carrier Frequency Division Multiple Access (“SC-FDMA”) scheme or an OFDM scheme. More generally, however, the wireless communication system 100 may implement some other open or proprietary communication protocol, for example, WiMAX, IEEE 802.11 variants, GSM, GPRS, UMTS, LTE variants, CDMA2000, Bluetooth®, ZigBee, Sigfoxx, among other protocols. The present disclosure is not intended to be limited to the implementation of any particular wireless communication system architecture or protocol.

[0037] The network units 104 may serve a number of remote units 102 within a serving area, for example, a cell or a cell sector via a wireless communication link. The network units 104 transmit DL communication signals to serve the remote units 102 in the time, frequency, and/ or spatial domain.

[0038] Figure 2 depicts a user equipment apparatus 200 that may be used for implementing the methods described herein. The user equipment apparatus 200 is used to implement one or more of the solutions described herein. The user equipment apparatus 200 is in accordance with one or more of the user equipment apparatuses described in embodiments herein. In particular, the user equipment apparatus 200 may comprise a UE 102 from Figure 1, a UE 680 from Figure 6, a UE represented by 1270 in Figure 12, for instance. The user equipment apparatus 200 includes a processor 205, a memory 210, an input device 215, an output device 220, and a transceiver 225.

[0039] The input device 215 and the output device 220 may be combined into a single device, such as a touchscreen. In some implementations, the user equipment apparatus 200 does not include any input device 215 and/ or output device 220. The user equipment apparatus 200 may include one or more of: the processor 205, the memory 210, and the transceiver 225, and may not include the input device 215 and/ or the output device 220.

[0040] As depicted, the transceiver 225 includes at least one transmitter 230 and at least one receiver 235. The transceiver 225 may communicate with one or more cells (or wireless coverage areas) supported by one or more base units. The transceiver 225 may be operable on unlicensed spectrum. Moreover, the transceiver 225 may include multiple UE panels supporting one or more beams. Additionally, the transceiver 225 may support at least one network interface 240 and/ or application interface 245. The application interface(s) 245 may support one or more APIs. The network interface(s) 240 may support 3GPP reference points, such as Uu, Nl, PC5, etc. Other network interfaces 240 may be supported, as understood by one of ordinary skill in the art.

[0041] The processor 205 may include any known controller capable of executing computer-readable instructions and/ or capable of performing logical operations. For example, the processor 205 may be a microcontroller, a microprocessor, a central processing unit (“CPU”), a graphics processing unit (“GPU”), an auxiliary processing unit, a field programmable gate array (“FPGA”), or similar programmable controller. The processor 205 may execute instructions stored in the memory 210 to perform the methods and routines described herein. The processor 205 is communicatively coupled to the memory 210, the input device 215, the output device 220, and the transceiver 225. [0042] The processor 205 may control the user equipment apparatus 200 to implement the user equipment apparatus behaviors described herein. The processor 205 may include an application processor (also known as “main processor”) which manages application-domain and operating system (“OS”) functions and a baseband processor (also known as “baseband radio processor”) which manages radio functions.

[0043] The memory 210 may be a computer readable storage medium. The memory 210 may include volatile computer storage media. For example, the memory 210 may include a RAM, including dynamic RAM (“DRAM”), synchronous dynamic RAM (“SDRAM”), and/ or static RAM (“SRAM”). The memory 210 may include non-volatile computer storage media. For example, the memory 210 may include a hard disk drive, a flash memory, or any other suitable non-volatile computer storage device. The memory 210 may include both volatile and non-volatile computer storage media.

[0044] The memory 210 may store data related to implement a traffic category field as described herein. The memory 210 may also store program code and related data, such as an operating system or other controller algorithms operating on the apparatus 200. [0045] The input device 215 may include any known computer input device including a touch panel, a button, a keyboard, a stylus, a microphone, or the like. The input device 215 may be integrated with the output device 220, for example, as a touchscreen or similar touch-sensitive display. The input device 215 may include a touchscreen such that text may be input using a virtual keyboard displayed on the touchscreen and/ or by handwriting on the touchscreen. The input device 215 may include two or more different devices, such as a keyboard and a touch panel.

[0046] The output device 220 may be designed to output visual, audible, and/ or haptic signals. The output device 220 may include an electronically controllable display or display device capable of outputting visual data to a user. For example, the output device 220 may include, but is not limited to, a Liquid Crystal Display (“LCD”), a Light- Emitting Diode (“LED”) display, an Organic LED (“OLED”) display, a projector, or similar display device capable of outputting images, text, or the like to a user. As another, non-limiting, example, the output device 220 may include a wearable display separate from, but communicatively coupled to, the rest of the user equipment apparatus 200, such as a smart watch, smart glasses, a heads-up display, or the like. Further, the output device 220 may be a component of a smart phone, a personal digital assistant, a television, a table computer, a notebook (laptop) computer, a personal computer, a vehicle dashboard, or the like.

[0047] The output device 220 may include one or more speakers for producing sound. For example, the output device 220 may produce an audible alert or notification (e.g., a beep or chime). The output device 220 may include one or more haptic devices for producing vibrations, motion, or other haptic feedback. All, or portions, of the output device 220 may be integrated with the input device 215. For example, the input device 215 and output device 220 may form a touchscreen or similar touch-sensitive display. The output device 220 may be located near the input device 215.

[0048] The transceiver 225 communicates with one or more network functions of a mobile communication network via one or more access networks. The transceiver 225 operates under the control of the processor 205 to transmit messages, data, and other signals and also to receive messages, data, and other signals. For example, the processor 205 may selectively activate the transceiver 225 (or portions thereof) at particular times in order to send and receive messages.

[0049] The transceiver 225 includes at least one transmitter 230 and at least one receiver 235. The one or more transmitters 230 may be used to provide uplink communication signals to a base unit of a wireless communication network. Similarly, the one or more receivers 235 may be used to receive downlink communication signals from the base unit. Although only one transmitter 230 and one receiver 235 are illustrated, the user equipment apparatus 200 may have any suitable number of transmitters 230 and receivers 235. Further, the trans mi tter(s) 230 and the receiver(s) 235 may be any suitable type of transmitters and receivers. The transceiver 225 may include a first transmitter/receiver pair used to communicate with a mobile communication network over licensed radio spectrum and a second transmitter/receiver pair used to communicate with a mobile communication network over unlicensed radio spectrum.

[0050] The first transmitter/ receiver pair may be used to communicate with a mobile communication network over licensed radio spectrum and the second transmitter/ receiver pair used to communicate with a mobile communication network over unlicensed radio spectrum may be combined into a single transceiver unit, for example a single chip performing functions for use with both licensed and unlicensed radio spectrum. The first transmitter /receiver pair and the second transmitter/receiver pair may share one or more hardware components. For example, certain transceivers 225, transmitters 230, and receivers 235 may be implemented as physically separate components that access a shared hardware resource and/ or software resource, such as for example, the network interface 240.

[0051] One or more transmitters 230 and/ or one or more receivers 235 may be implemented and/ or integrated into a single hardware component, such as a multitransceiver chip, a system-on-a-chip, an Application-Specific Integrated Circuit (“ASIC”), or other type of hardware component. One or more transmitters 230 and/ or one or more receivers 235 may be implemented and/ or integrated into a multi-chip module. Other components such as the network interface 240 or other hardware components/ circuits may be integrated with any number of transmitters 230 and/ or receivers 235 into a single chip. The transmitters 230 and receivers 235 may be logically configured as a transceiver 225 that uses one more common control signals or as modular transmitters 230 and receivers 235 implemented in the same hardware chip or in a multi-chip module.

[0052] Figure 3 depicts further details of the network node 300 that may be used for implementing the methods described herein. The network node 300 may be one implementation of an entity in the wireless communication network, e.g. in one or more of the wireless communication networks described herein. The network node 300 may comprise a NWDAF 610 (including MTLF 601 and FL server 602) from Figure 6, NEF 620 from Figure 6, AnLF 1110- or NRF 1120 or NEF 1130 or MTLF 1140 from Figure 11, AnLF 1220 or NRF 1230 or MTLF 1240 or NEF 1250, from Figure 12, for instance. The network node 300 includes a processor 305, a memory 310, an input device 315, an output device 320, and a transceiver 325.

[0053] The input device 315 and the output device 320 may be combined into a single device, such as a touchscreen. In some implementations, the network node 300 does not include any input device 315 and/ or output device 320. The network node 300 may include one or more of: the processor 305, the memory 310, and the transceiver 325, and may not include the input device 315 and/ or the output device 320.

[0054] As depicted, the transceiver 325 includes at least one transmitter 330 and at least one receiver 335. Here, the transceiver 325 communicates with one or more remote units 200. Additionally, the transceiver 325 may support at least one network interface 340 and/ or application interface 345. The application interface(s) 345 may support one or more APIs. The network interface(s) 340 may support 3GPP reference points, such as Uu, Nl, N2 and N3. Other network interfaces 340 may be supported, as understood by one of ordinary skill in the art.

[0055] The processor 305 may include any known controller capable of executing computer-readable instructions and/ or capable of performing logical operations. For example, the processor 305 may be a microcontroller, a microprocessor, a CPU, a GPU, an auxiliary processing unit, a FPGA, or similar programmable controller. The processor 305 may execute instructions stored in the memory 310 to perform the methods and routines described herein. The processor 305 is communicatively coupled to the memory 310, the input device 315, the output device 320, and the transceiver 325.

[0056] The memory 310 may be a computer readable storage medium. The memory 310 may include volatile computer storage media. For example, the memory 310 may include a RAM, including dynamic RAM (“DRAM”), synchronous dynamic RAM (“SDRAM”), and/ or static RAM (“SRAM”). The memory 310 may include non-volatile computer storage media. For example, the memory 310 may include a hard disk drive, a flash memory, or any other suitable non-volatile computer storage device. The memory 310 may include both volatile and non-volatile computer storage media.

[0057] The memory 310 may store data related to establishing a multipath unicast link and/ or mobile operation. For example, the memory 310 may store parameters, configurations, resource assignments, policies, and the like, as described herein. The memory 310 may also store program code and related data, such as an operating system or other controller algorithms operating on the network node 300.

[0058] The input device 315 may include any known computer input device including a touch panel, a button, a keyboard, a stylus, a microphone, or the like. The input device 315 may be integrated with the output device 320, for example, as a touchscreen or similar touch-sensitive display. The input device 315 may include a touchscreen such that text may be input using a virtual keyboard displayed on the touchscreen and/ or by handwriting on the touchscreen. The input device 315 may include two or more different devices, such as a keyboard and a touch panel.

[0059] The output device 320 may be designed to output visual, audible, and/ or haptic signals. The output device 320 may include an electronically controllable display or display device capable of outputting visual data to a user. For example, the output device 320 may include, but is not limited to, an LCD display, an LED display, an OLED display, a projector, or similar display device capable of outputting images, text, or the like to a user. As another, non-limiting, example, the output device 320 may include a wearable display separate from, but communicatively coupled to, the rest of the network node 300, such as a smart watch, smart glasses, a heads-up display, or the like. Further, the output device 320 may be a component of a smart phone, a personal digital assistant, a television, a table computer, a notebook (laptop) computer, a personal computer, a vehicle dashboard, or the like.

[0060] The output device 320 may include one or more speakers for producing sound. For example, the output device 320 may produce an audible alert or notification (e.g., a beep or chime). The output device 320 may include one or more haptic devices for producing vibrations, motion, or other haptic feedback. All, or portions, of the output device 320 may be integrated with the input device 315. For example, the input device 315 and output device 320 may form a touchscreen or similar touch-sensitive display. The output device 320 may be located near the input device 315.

[0061] The transceiver 325 includes at least one transmitter 330 and at least one receiver 335. The one or more transmitters 330 may be used to communicate with the UE, as described herein. Similarly, the one or more receivers 335 may be used to communicate with network functions in the PLMN and/ or RAN, as described herein. Although only one transmitter 330 and one receiver 335 are illustrated, the network node 300 may have any suitable number of transmitters 330 and receivers 335. Further, the transmitter(s) 330 and the receiver(s) 335 may be any suitable type of transmitters and receivers.

[0062] Figure 4 illustrates an embodiment 400 of a high-level SEAL ADAE architecture as specified in 3GPP TS 23.434. The embodiment 400 includes a VAL UE 410, a 3GPP network system 420, a VAL server(s) 430 and an application data analytics enablement server 440. The VAL UE 410 is illustrated as comprising a VAL client(s) 401 and an application data analytics enablement client 402. The separate VAL layer 450 and SEAL layer 460 in the embodiment 400 are also illustrated. The VAL layer 450 itself comprising the VAL client(s) 401 and VAL server(s) 430. The SEAL layer 460 comprising the application data analytics enablement client 402 and the application data analytics enablement server 440. The VAL client(s) 401 is illustrated as communicating over 3GPP network system 420 to VAL server(s) 430 using VAL-UU. The VAL client(s) 401 is also shown as communicating with the application data analytics enablement client 401 using ADAE-C. The application data analytics enablement client 401 is further shown communicating over 3GPP network system 420 to the application data analytics enablement server 440 using ADAE-UU. The application data analytics enablement server 440 is further shown communicating with 3GPP network system 420 using N33, N6 and ADAE-OAM. The application data analytics enablement server 440 us further shown communicating with VAL server(s) 430 using ADAE-S.

[0063] More specifically, the embodiment 400 shows a high-level architecture for ADAE service. In this figure, the VAL server(s) 430 communicates with the AD AES 440 over the ADAE-S reference point. The AD AES 440, acting as AF, may communicate with the 5G Core Network functions in 3GPP network system 420 (over N33 reference point to NEF and N6 reference point to UPF) and OAM (over ADAE-OAM interface). [0064] Figure 5 illustrates an embodiment 500 of a coordinated AD AES deployment model as specified in 3GPP TS 23.436. The embodiment 500 includes an EDN Al 510, an EDN A2 520, a centralized DN (DNN-B) 530 and a PLMN 540. The EDN Al 510 comprises a plurality of EAS 511, an EES 512 and an ADAE server #1.1 513. The EDN A2 520 comprises a plurality of EAS 521, an EES 522 and an ADAE server #1.2 523. The centralized DN 530 comprises a plurality of VAL servers 531 and SEAL services 532 comprising ADAE server #1 533. The PLMN 540 comprises an ADAE 1.1 service area 541 and an ADAE 1.2 service area 542. EDN Al 510 is shown interfacing with PLMN 540 by DNAI Al-m 550 and DNAI Al-n 560. EDN A2 520 is shown interfacing with PLMN 540 by NDAI A2-n 570. The centralized DN 530 is shown interfacing with PLMN 540 by DNAI B 580.

[0065] More specifically, in the coordinated deployment 500, as stated at TS 23.436, multiple AD AES 513, 523, 533, can be located at different external data networks (EDNs)/data networks (DNs) 510, 520, 530 and can be deployed by the same ADAE provider. Such coordinated deployments allow the local — global analytics derivation (which may be needed for improving the analytics confidence level) . The centrally deployed AD AES can also act as ADAE analytics aggregator and controls the edge deployed AD AES to derive analytics on different sub-areas. One example is the use of analytics for the EDN#1 510 or EDN#2 520 load, which will help predicting the VAL server 531 performance at a centrally located AD AES 533. An alternative deployment is applicable for ML-based analytics methods, like supervised learning, where the centrally located AD AES 533 acts as ML model training entity, and the edge located ADAESs 513 and 523 can act as ML model inference entities (using edge data to improve the prediction accuracy) .

[0066] The statistics /predictions of the edge deployed AD AES 513 and 523 correspond to the AD AES service areas 541 and 541, which is equivalent to the EES/EAS service areas. The central ADAE server 533 covers all PLMN 540 areas and is used to coordinate (in case of central AD AES performing aggregation) or jointly perform analytics (in case of distributed analytics derivation, e.g., for ML model training and inference in central and de-centralized AD AES) with the distributed AD AES 513 and 523. Such analytics services can be provided to consumers at the central DN 530, like the VAL servers 531 or SEAL services 532 or even at the PLMN 540 side (e.g., NWDAF consuming service experience analytics).

[0067] The solution provided by this disclosure, is to allow external FL clients to collaborate with a core network. An ‘external’ FL client is considered as being an FL client that is external to the core network. Such an FL client can for example reside at AF / AD AES/ app at the UE side (for the case of vertical domain FL).

[0068] The use case for an AF being an FL client is the case when the data producer resides at the DN side and the AF is expected to handle the local ML model training, instead of sending raw data. One particular case is the one having an analytics entity at DN side, namely AD AES, which has the capability of performing analytics, and can serve as candidate FL client for the respective DN (or EDN).

[0069] Another use case is to allow the application at the UE side performing FL as a client. This particular case is for scenarios where local UE data are expected to be provided to NWDAF for performing ML operations; however, such data may not be exposed from the device side to the 5GC and the use of an FL client at the UE side may be preferable (for example to train data related to UE app performance (e.g. channel losses, rate, QoE) or for providing mobility patterns based on location reports at the UE side). In such a scenario, the FL client can be an application at the UE or an enabler client (e.g., AD AEG) at the UE side which acts as a middleware app to perform the FL for a specific analytics event.

[0070] Currently, the NWDAF solutions explored in 3GPP SA2 for federated learning assume that the ML training entities reside at the same 5G core domain under the same administration. However, if we assume that an application entity is performing the ML training, the data used locally can solve issues related to raw data exposure willingness by the 3rd party to a MNO.

[0071] Figure 6 illustrates an embodiment 600 of ML federated learning deployment. The embodiment 600 illustrates an NWDAF 610 comprising an MTLF 601 comprising an FL server 602. Also shown is a NEF 620 through which NWDAF 610 can communicate with an AF/FL client 630, an AD AES FL client 650 and a device application/ FL client 670. The AF/FL client 630 performs model training and performs data collection with a data producer 640 at the vertical domain. The AD AES FL client 650 performs model training and performs data collection with a data producer VAL server 660. The device application/ FL client 670 performs model training and performs data collection with a data producer UE 680. The NWDAF 610, NEF 620, AF/FL client 630, data producer at vertical domain 640, AD AES FL client 650, data producer VAL server 660, device application/FL client 670, are all shown as being part of the federated learning 690.

[0072] More specifically the NWDAF 610 includes MTLF 601 and in particular an FL server 602. The FL clients 630, 650, 670, reside at the DN/3rd party, which can be trusted (e.g., trusted AF, middleware AF) or untrusted (e.g., a UE application) or can be also a 3rd party analytics entity (e.g. AD AES). In this deployment, one key aspect is how to allow the 3rd party FL client 630, 650, 670, to register to 5GC its capability, to allow the discovery from FL server 602. The high-level steps for the registration/discovery aspects will now be described.

[0073] An external function (which can be a potential FL client) with AF capability requests to register to a network repository its FL client capability. This can be performed at the AF registration phase or based on a trigger. Such trigger can be the request of an analytics service from a NWDAF, the instantiation of an application, or the query from a NWDAF for data from the application. The trigger can be at least one of the following: an analytics service gets initiated (FL enabled); an application service which requires analytics services is activated / starts running; the analytics performance is lower than the expected, and the possibility of FL using diverse FL types is indicated by the external function (or at the MTLF) - this requires that the analytics service is running, and the external function is the consumer; NWDAF identifies the need for external data to meet the analytics service performance targets and generates a trigger event to query for external candidate FL clients; NWDAF determines that analytic data is required by external FL client if a target UE belongs to a different PLMN and is roaming to the HPLMN or if the target UE belongs to HPLMN and is roaming to a VPLMN.

[0074] The network registry authorizes the request and stores the FL client profile information (for the case of trusted AF), including the AF ID /application ID and address as well as the capability (for which analytics ID/ event ID it can serve as FL client, processing capabilities), exposure limitations (whether this needs to be via NEF or directly, based on whether AF is in trusted domain), data types supported and availability, time and area of FL client support. If the candidate FL is untrusted then the FL client capabilities need to be mapped at the NEF; and register the NEF with the corresponding FL capabilities related to the client FL, assuming that the external FL client is the AF. If the external FL client is a data producer belonging to a different PLMN then the request goes via another type of NEF.

[0075] NWDAF (AnLF) subscribes to central MTLF for ML model provisioning, and MTLF determines that FL is required. It optionally determines the need for external data sources and possibility of allowing external FL clients for these sources.

[0076] MTLF performs a discovery request to the network registry, also including the preference/ flag to discover external FL clients. Such preference / flag indicates whether external FL clients need to be discovered and can also indicate whether the FL clients to be discovered are allowed to be trusted or untrusted sources.

[0077] The registry authorizes the request and lists the FL clients available including the external ones and sends this as a discovery response to the MTLF.

[0078] For the purposes of the disclosure herein, a reference to an ‘exposure function’ includes functions /entities such as NEF and CAPIF AEF; a reference to a ‘ML model training server function’ includes functions /entities such as NWDAF MTLF; a reference to an ‘analytics function’ includes functions /entities such as NWDAF AnLF; a reference to an ‘external ML model training client function’ includes functions /entities such as FL client AF, UE, or AD AES; and a reference to ‘service registry’ includes functions /entities such as NRF, UDR, CCF, external registry, edge platform registry, app registry, and DN registry. Furthermore, in this mechanism there is mention of MTLF as a NF - however this can be generalized such that the ML Model training server function can be also within the DN/EDN side (e.g. central AD AES performing this role).

[0079] The disclosure herein provides an application entity in a wireless communication system, comprising a processor; and a memory coupled with the processor, the processor configured to cause the application entity to receive, from at least one other network or application entity of a wireless communication system, a query for acting as a federated learning participant for a particular machine learning enabled analytics event, wherein the wireless communication system comprises a core network; determine, for the particular machine learning enabled analytics event, a federated learning client profile, wherein the federated learning client profile comprises a capability of the application entity to act as a federated learning client for at least one data source that is external to the core network, and/ or to act as a data source that is external to the core network, for the particular machine learning enabled analytics event; and transmit, to a service registry entity, a request for registering a registration information, the registration information comprising the federated learning client profile and an identifier for the application entity.

[0080] In some embodiments, the processor is configured to cause the application entity, in determining a federated learning client profile, to determine whether a data source that is external to the core network, can be exposed to the at least one other network or application entity for the purposes of the particular machine learning enabled analytics event.

[0081] In some embodiments, the processor is further configured to cause the application entity to transmit, to the at least one other network or application entity, an indication that machine learning using the data source that is external to the core network, can be performed at an external data network that is external to the core network.

[0082] In some embodiments, the query for acting as a federated learning participant, comprises a request for data for the particular machine learning enabled analytics event. [0083] In some embodiments, the query for acting as a federated learning participant comprises, an indication that federated learning is to be utilized for the particular machine learning-enabled analytics event.

[0084] In some embodiments, the registration information comprises an application function identifier; an application identifier; an application data analytics enabler service identifier; a user equipment identifier; an identifier for a supported analytics type; a serving area, comprising a geographical and/ or topological area; an identifier for a local data source; and/ or a preferred time period for federated learning. A ‘topological area’ corresponds to a network defined area, such as a cell area or tracking area or a set of cell areas. A topological area can be identified by the cell ID, for instance.

[0085] In some embodiments, the service registry entity is a service registry entity selected from the list of service registries consisting of a network repository function; a common application programming interface framework core function; a user data repository; an application registry; a data network registry; and an edge or cloud registry. [0086] In some embodiments, the at least one other network or application entity comprises at least one network or application entity selected from the list consisting of a network exposure function; a data analytics function; and a machine learning model training logical function. [0087] Figure 7 illustrates an embodiment 700 of a method in an application entity. A first step 710 comprises, receiving, from at least one other network or application entity of a wireless communication system, a query for acting as a federated learning participant for a particular machine learning enabled analytics event, wherein the wireless communication system comprises a core network.

[0088] A further step 720 comprises, determining, for the particular machine learning enabled analytics event, a federated learning client profile, wherein the federated learning client profile comprises a capability of the application entity to act as a federated learning client for at least one data source that is external to the core network, and/ or to act as a data source that is external to the core network, for the particular machine learning enabled analytics event.

[0089] A further step 730 comprises, transmitting, to a service registry entity, a request for registering a registration information, the registration information comprising the federated learning client profile and an identifier for the application entity.

[0090] In some embodiments, the determining a federated learning client profile, comprises determining whether a data source that is external to the core network, can be exposed to the at least one other network or application entity for the purposes of the particular machine learning enabled analytics event.

[0091] In certain embodiments, the method 700 may be performed by a processor executing program code, for example, a microcontroller, a microprocessor, a CPU, a GPU, an auxiliary processing unit, a FPGA, or the like.

[0092] Some embodiments further comprise transmitting, to the at least one other network or application entity, an indication that machine learning using the data source that is external to the core network, can be performed at an external data network that is external to the core network.

[0093] In some embodiments, the query for acting as a federated learning participant, comprises a request for data for the particular machine learning enabled analytics event. [0094] In some embodiments, the query for acting as a federated learning participant comprises, an indication that federated learning is to be utilized for the particular machine learning-enabled analytics event.

[0095] In some embodiments, the registration information comprises an application function identifier; an application identifier; an application data analytics enabler service identifier; a user equipment identifier; an identifier for a supported analytics type; a serving area, comprising a geographical and/ or topological area; an identifier for a local data source; and/ or a preferred time period for federated learning. A ‘topological area’ corresponds to a network defined area, such as a cell area or tracking area or a set of cell areas. A topological area can be identified by the cell ID, for instance.

[0096] In some embodiments, the service registry entity is a service registry entity selected from the list of service registries consisting of a network repository function; a common application programming interface framework core function; a user data repository; an application registry; a data network registry; and an edge or cloud registry. [0097] In some embodiments, the at least one other network or application entity comprises at least one network or application entity selected from the list consisting of a network exposure function; a data analytics function; and a machine learning model training logical function.

[0098] The disclosure herein also provides a server entity in a wireless communication system, comprising a processor; and a memory coupled with the processor, the processor configured to cause the server entity to: determine a federated learning requirement for a particular machine learning enabled analytics event, wherein the federated learning requirement uses at least one application entity that is external to a core network of the wireless communication system; and transmit, to a service registry entity, a request to discover information of the at least one application entity, based on the federated learning requirement.

[0099] In some embodiments, the processor is configured to cause the server entity to query, the at least one application entity, for acting as a federated learning participant for the particular machine learning enabled analytics event.

[0100] In some embodiments, the query for acting as a federated learning participant comprises, a request for data for the particular machine learning enabled analytics event. [0101] In some embodiments the query for acting as a federated learning participant comprises, an indication that federated learning is to be utilized for the particular machine learning-enabled analytics event.

[0102] In some embodiments, the processor is configured to cause the server entity, in determining a federated learning requirement, to receive, from a network entity, a request for a trained machine learning model associated with the particular machine learning enabled analytics event; and determine the federated learning requirement based at least in part on the request for the trained machine learning model. [0103] In some embodiments, the request for a trained machine learning model comprises an identifier for the particular machine learning enabled analytics event; and a machine learning model area of interest.

[0104] In some embodiments, the request to discover information, comprises the identifier for the particular machine learning enabled analytics event; an indication of federated learning; a time period of interest for federated learning; and an indication for discovery of one or more federated learning clients for at least one data source that is external to the core network and/ or for discovery of at least one data source that is external to the core network, for the particular machine learning enabled analytics event. [0105] In some embodiments, the service registry entity is a service registry entity selected from the list of service registries consisting of: a network repository function; a common application programming interface framework core function; a user data repository; an application registry; a data network registry; and an edge or cloud registry.

[0106] In some embodiments, the server entity is selected from the list of server entities consisting of a network exposure function; a data analytics function; and a machine learning model training logical function.

[0107] In some embodiments, requests/ responses/ communications that are to/ from untrusted sources may be sent via a NEF.

[0108] Figure 8 illustrates an embodiment 800 of a method in a server entity, the server entity in a wireless communication system. A first step 810 comprises determining a federated learning requirement for a particular machine learning enabled analytics event, wherein the federated learning requirement uses at least one application entity that is external to a core network of the wireless communication system. A further step 820 comprises transmitting, to a service registry entity, a request to discover information of the at least one application entity, based on the federated learning requirement.

[0109] In certain embodiments, the method 800 may be performed by a processor executing program code, for example, a microcontroller, a microprocessor, a CPU, a GPU, an auxiliary processing unit, a FPGA, or the like.

[0110] Some embodiments further comprise querying, the at least one application entity, for acting as a federated learning participant for the particular machine learning enabled analytics event.

[0111] In some embodiments, the querying for acting as a federated learning participant comprises, requesting data for the particular machine learning enabled analytics event. [0112] In some embodiments the querying for acting as a federated learning participant comprises, indicating that federated learning is to be utilized for the particular machine learning-enabled analytics event.

[0113] In some embodiments, the determining a federated learning requirement comprises receiving, from a network entity, a request for a trained machine learning model associated with the particular machine learning enabled analytics event; and determining the federated learning requirement based at least in part on the request for the trained machine learning model.

[0114] In some embodiments, the request for a trained machine learning model comprises an identifier for the particular machine learning enabled analytics event; and a machine learning model area of interest.

[0115] In some embodiments, the request to discover information, comprises the identifier for the particular machine learning enabled analytics event; an indication of federated learning; a time period of interest for federated learning; and an indication for discovery of one or more federated learning clients for at least one data source that is external to the core network and/ or for discovery of at least one data source that is external to the core network, for the particular machine learning enabled analytics event. [0116] In some embodiments, the service registry entity is a service registry entity selected from the list of service registries consisting of: a network repository function; a common application programming interface framework core function; a user data repository; an application registry; a data network registry; and an edge or cloud registry. [0117] In some embodiments, the server entity is selected from the list of server entities consisting of a network exposure function; a data analytics function; and a machine learning model training logical function.

[0118] In some embodiments, requests/ responses/ communications that are to/ from untrusted sources may comprise sending and/ or receiving said requests/responses/communications via a NEF.

[0119] The disclosure herein also provides a service registry entity in a wireless communication system, comprising: a processor; and a memory coupled with the processor, the processor configured to cause the service registry entity to: receive, from at least one application entity external to a core network of the wireless communication system, a request for registering a registration information, the registration information comprising an identity of the respective application entity and a respective federated learning client profile, wherein the federated learning client profile comprises a capability of the respective application entity to act as a federated learning client for at least one data source that is external to the core network and/ or to act as a data source that is external to the core network, for a particular machine learning enabled analytics event; and store, in the memory, the registration information.

[0120] In some embodiments, the processor is further configured to cause the service registry entity to receive, from a server entity, a request to discover information of at least one application entity acting as a federated learning client for at least one data source that is external to the core network and/ or acting as a data source that is external to the core network, for a particular machine learning enabled analytics event; fetch, from the memory, discovery information, wherein the discovery information comprises at least one of the stored registration information; and transmit the discovery information, to the server entity.

[0121] In some embodiments, the processor is further configured to cause the service registry entity to authorize the request to discover information.

[0122] In some embodiments, the registration information comprises an application function identifier; an application identifier; an application data analytics enabler service identifier; a user equipment identifier; an identifier for a supported analytics type; a serving area, comprising a geographical and/ or topological area; an identifier for a local data source; and/ or a preferred time period for federated learning. A ‘topological area’ corresponds to a network defined area, such as a cell area or tracking area or a set of cell areas. A topological area can be identified by the cell ID, for instance.

[0123] In some embodiments, the service registry entity is a service registry entity selected from the list of service registries consisting of a network repository function; a common application programming interface framework core function; a user data repository; an application registry; a data network registry; and an edge or cloud registry. [0124] In some embodiments, the service registry is a NEF. In such embodiments the NEF must support a mapping of applications /entities to federated learning capabilities and the registration thereof.

[0125] In some embodiments, the processor is further configured to cause the service registry entity store, in the memory, for each registration information, an indication that the registration information relates to an application entity that is external to the core network of the wireless communication system. [0126] In some embodiments, the processor is configured to cause the service registry entity to transmit, to the at least one application entity, a response to the request for registering the registration information.

[0127] In some embodiments, an NRF may point to an app registry and an MTLF may send discovery requests directly to the app registry.

[0128] Figure 9 illustrates an embodiment 900 of a method in a service registry. A first step 910 comprises receiving, from at least one application entity external to a core network of a wireless communication system, a request for registering a registration information, the registration information comprising an identity of the respective application entity and a respective federated learning client profile, wherein the federated learning client profile comprises a capability of the respective application entity to act as a federated learning client for at least one data source that is external to the core network and/ or to act as a data source that is external to the core network, for a particular machine learning enabled analytics event. A further step 920 comprises storing the registration information.

[0129] In certain embodiments, the method 900 may be performed by a processor executing program code, for example, a microcontroller, a microprocessor, a CPU, a GPU, an auxiliary processing unit, a FPGA, or the like.

[0130] Some embodiments comprise receiving, from a server entity, a request to discover information of at least one application entity acting as a federated learning client for at least one data source that is external to the core network and/ or acting as a data source that is external to the core network, for a particular machine learning enabled analytics event; fetch, from the memory, discovery information, wherein the discovery information comprises at least one of the stored registration information; and transmitting the discovery information, to the server entity.

[0131] Some embodiments comprise authorizing the request to discover information. [0132] In some embodiments, the registration information comprises an application function identifier; an application identifier; an application data analytics enabler service identifier; a user equipment identifier; an identifier for a supported analytics type; a serving area, comprising a geographical and/ or topological area; an identifier for a local data source; and/ or a preferred time period for federated learning. A ‘topological area’ corresponds to a network defined area, such as a cell area or tracking area or a set of cell areas. A topological area can be identified by the cell ID, for instance. [0133] In some embodiments, the service registry entity is a service registry entity selected from the list of service registries consisting of a network repository function; a common application programming interface framework core function; a user data repository; an application registry; a data network registry; and an edge or cloud registry. [0134] In some embodiments, the service registry is a NEF. In such embodiments the NEF must support a mapping of applications/ entities to federated learning capabilities and the registration thereof.

[0135] Some embodiments further comprise storing, for each registration information, an indication that the registration information relates to an application entity that is external to the core network of the wireless communication system.

[0136] Some embodiments comprise transmitting, to the at least one application entity, a response to the request for registering the registration information.

[0137] In some embodiments, an NRF may point to an app registry and an MTLF may send discovery requests directly to the app registry.

[0138] The disclosure herein also provides an exposure entity in a wireless communication system, comprising a memory and a processor coupled to the memory, wherein the processor is configured to cause the exposure entity to: map an identifier of an application entity to a federated learning client profile associated with the application entity, wherein the federated learning client profile comprises a capability of the application entity to act as a federated learning client for at least one data source that is external to a core network of a wireless communication network and/ or to act as a data source that is external to the core network, for a particular machine learning enabled analytics event.

[0139] In some embodiments, the processor is further configured to cause the exposure entity to receive a request for an application entity acting as a federated learning client for at least one data source that is external to the core network and/ or acting as a data source that is external to the core network, for the particular machine learning enabled analytics event; translate the request to register the application entity based on the mapping; and send the translated registration request to a service registry entity.

[0140] Figure 10 illustrates an embodiment 1000 of a method in an exposure function. A first step 1010 comprises mapping an identifier of an application entity to a federated learning client profile associated with the application entity, wherein the federated learning client profile comprises a capability of the application entity to act as a federated learning client for at least one data source that is external to a core network of a wireless communication network and/ or to act as a data source that is external to the core network, for a particular machine learning enabled analytics event.

[0141] Some embodiments comprise receiving a request for an application entity acting as a federated learning client for at least one data source that is external to the core network and/ or acting as a data source that is external to the core network, for the particular machine learning enabled analytics event; translating the request to register the application entity based on the mapping; and sending the translated registration request to a service registry entity.

[0142] Figure 11 illustrates an embodiment 1100 of registration and discovery via an NRF for a trusted AF. This implementation is for the case when a candidate FL client is a trusted AF. The figure illustrates an AnLF 1110, an NRF 1120, a NEF 1130, a MTLF FL server 1140, an AF candidate FL client 1150 and a data producer 1160.

[0143] In a first step 1101, NWDAF MTLF- 1140 attempts to subscribe to a candidate client 1150 for a particular analytics event or ML model identity or optionally queries a trusted AF (for a given application) whether data are accessible for ML-enabled analytics. NWDAF MTLF 1140 also optionally indicates that FL is possible. This can be done via two ways. Either invoking anNaf specific API or an Nmtlf API to be defined in eNA. [0144] In a subsequent step 1102, the trusted AF 1150 checks with the data producer application 1160 and its policies/permissions, whether it is feasible to expose data to the 5GC for ML enabled analytics. Optionally the AF 1150 may respond to NWDAF MTLF 1140 that such exposure is not possible but it is possible to train the data locally at the DN side.

[0145] In a subsequent step 1103, the trusted AF 1150 (e.g., AF, AD AES) with FL capability registers to a repository (NRF 1120) its FL client profile. This can include the AF ID or AppID or AD AES ID, Supported Analytics ID(s), Serving Area, List of Data Source IDs, preferred Time Period for FL). This is illustrated as an AF FL client registration request.

[0146] In a subsequent step 1104, NRF 1120 stores the FL client profile and indicates that the FL client is an external entity.

[0147] In a subsequent step 1105, NRF 1120 also sends a registration response to the function 1150 acting as FL client. This is illustrated as a registration response.

[0148] In a further step 1106, the AnLF 1110 subscribes to a trained ML Model associated with an Analytics ID by invoking the NnwdafoMLModelProvision (Analytics ID, ML model Filter (S-NSSAI, Area of Interest)) service operation. This is illustrated as subscribe/MLModelProvision.

[0149] As the MTLF 1140 with FL server lacks data over the Area of Interest requested by the AnLF 1110, it determines that training shall be based on Vertical FL clients which have the data of the area of interest and could be used for Vertical Federated Learning via the NRF 1120.

[0150] In a further step 1107, NWDAF/MTLF 1140 including an FL server detects that FL clients are needed and in particular FL clients for data which is not available (e.g., 3rd party data). Such detection can be based on the analytics performance (for example if this doesn’t meet the requirements).

[0151] In a further step 1108, NWDAF/MTLF 1140 including an FL server sends a discovery request to NRF 1120 to discover available FL clients for the analytics ID, including the external ones. This is done by invoking the Nnrf_NFDiscovery_Request (an Analytics ID, vertical Federated Learning Indication, Serving Area, Time Period of Interest, external FL client indication) service operation. This is illustrated as a discovery request (FL client type).

[0152] In further steps 1109a and 1109b, NRF 1120 authorizes the discovery request and notifies the MTLF 1140 with FL server with the information of multiple external FL clients of different types (including AF, app of UE) and also information on how to reach these (e.g. via NEF 1130, API info etc). This is illustrated as a discovery response (external FL client info).

[0153] Figure 12 illustrates an embodiment 1200 of registration and discovery for an un trusted AF/UE. This implementation is for the case when a candidate FL client is an untrusted AF. The figure illustrates an AnLF 1220, a NRF 1230, a MTLF FL server 1240, a NEF 1250, a CCF/App Registry/UDR 1260, an untrusted AF candidate FL client 1270 and a data producer app 1280.

[0154] In a first step 1201, NWDAF MTLF 1240 attempts to subscribe to the candidate FL client 1270 to obtain data from an external application for a particular analytics event or for a data collection event or for a particular ML model identity/ profile. The request is provided to NEF 1250 (illustrated as 1201a trigger/ sub scribe for data), and NEF 1250 further queries the corresponding untrusted AF 1270 (for a given application, illustrated as 1201b query AF for data or acting as FL client) or an application at the UE (if SNA is used) whether data are accessible for ML-enabled analytics. NWDAF MTLF 1240 also optionally indicates that FL is possible. [0155] In a further step 1202, the AF/UE 1270 checks with the data producer application 1280 and its policies/permissions, whether it is feasible to expose data to the 5GC for ML enabled analytics. Optionally the AF/UE 1270 may respond to NWDAF MTLF 1240 (via NEF 1250) that such exposure is not possible but it is possible to train the data locally at the DN side.

[0156] In a further step 1203, the AF/UE 1270 with FL capability registers to a repository 1260 (CAPIF CCF or an edge/ cloud registry) its FL client profile. This can include the AF ID or AppID, Supported Analytics ID(s), Serving Area, List of Data Source IDs, preferred Time Period for FL). In case of UEs as FL clients., this includes the UE ID(s) and capabilities. This is illustrated as AF FL client registration request. [0157] In a further step 1204, the application registry 1260 (CAPIF CCF or an edge/ cloud registry) stores the FL client profile and indicates that the FL client is external entity.

[0158] In a further step 1205, the repository 1260 also sends a registration response to the function 1270 acting as FL client. This is illustrated as registration response.

[0159] In a further step 1206, the application repository 1260 may also provide some indication of possible FL clients outside 5GC to NRF 1230 or UDR. This can be in form of a registry ID/ address and supported FL client types, so as to allow the NWDAF MTLF 1240 to discover additional FL clients.

[0160] In a further step 1207, the AnLF 1220 subscribes to a trained ML Model associated with an Analytics ID by invoking the Nnwdaf_MLModelProvision (Analytics ID, ML model Filter (S-NSSAI, Area of Interest)) service operation. This is illustrated as subscribe/MLModelProvision.

[0161] As an alternative option, step 1206 may occur directly from the untrusted AF 1270 to NRF 1230 via NEF 1250. In that case, NRF 1230 is serving as the service registry. Hence step 1206, would replace steps 1203-1205 (step 1206 will be in form of a registration to NRF 1230 via NEF 1250). In this case, NEF 1250 capabilities need to be enhanced to have a mapping of AF-Service-ID or API Invoker ID to FL client capabilities; hence NEF 120 will register the capabilities on behalf of the untrusted AF 1270 to NRF 1230.

[0162] In a further step 1208, as the MTLF 1240 with FL server lacks data over the Area of Interest requested by the AnLF 1220, it determines that training based on Vertical Federated Learning is needed and is to discover FL clients which have the data of the area of interest and could be used for Vertical Federated Learning via the NRF 1230 or via the application registry 1260.

[0163] NWDAF/MTLF 1240 including an FL server detects that more FL clients are needed and in particular FL clients for data which is not available (e.g., 3rd party data). Such detection can be based on the analytics performance (for example if this doesn’t meet the requirements) .

[0164] In a further step 1209 NWDAF/MTLF 1240 including an FL server sends a discovery request to NRF 1230 to discover available FL clients for the analytics ID, including the external ones. This is done by invoking the Nnrf_NFDiscovery_Request (an Analytics ID, vertical Federated Learning Indication, Serving Area, Time Period of Interest, external FL client indication) service operation. This is illustrated as discovery request (FL client type).

[0165] In further steps 1210a-1210b, NRF 1230 authorizes the discovery request and notifies the MTLF 1240 with FL server with the information of multiple external FL clients of different types (including AF, app of UE) and also information on how to reach these (e.g. via NEF 1250, API info etc). This may include also the registry information to allow the discovery of particular capabilities of the external FL clients. This is illustrated as discovery response (external FL client info, registry info).

[0166] Different options are possible for steps 1207-1210. For example, NRF 1230 after receiving the FL client info from app registry 1260 (CCF, edge repository, edge UDR) provides all necessary info to MTLF 1240 via NEF 1250. Alternatively, NRF 1230 points to the app registry 1260 and MTLF 1240 sends a discovery request to the app registry 1260 via NEF 1250 (if the app registry 1260 is not the UDR or is not trusted).

[0167] MTLF 1240 when detecting the need for external candidate FL clients, may approach an external registry 1260 (or this can be done via NEF 1250 doing the mapping).

[0168] The NRF 1230 may be allowed to act as the only registry for untrusted AFs, and this requires that NEF 1250 supports the mapping to FL capabilities and the registration to NRF 1230.

[0169] The problem solved by the disclosure herein, is how to enable the application function to participate in the federated learning for ML-enabled NWDAF analytics. Such participation allows the application service provider and data producer to not expose its data and perform ML model training at the DN or UE side. [0170] This disclosure provides the needed procedure for allowing an application to register its capabilities for acting as FL client, and for allowing the NWDAF to discover the external AF capabilities acting as FL client for a given analytics event.

[0171] Other solutions do not assume that the FL client is outside the domain of the analytics function; hence the registration and discovery doesn’t take into account the exposure aspects and the interaction between network and DN/UE side.

[0172] In particular, the disclosure describes how a trusted AF registers to NRF its capabilities, and the discovery by NWDAF happens via querying the NRF. Furthermore, the disclosure herein describes how an un-trusted AF / application at UE registers its capabilities, and the discovery by NWDAF happens via querying NEF / CAPIF / an application registry.

[0173] More specifically, there is provided a method (at for instance an AF or external ML model training client function) for enabling an external application (itself associated with one or more data sources) to provide federated learning client services, the method comprising: receiving a trigger event for acting as an FL participant for an analytics event (the participant can be either as a data source or FL client), wherein the trigger event is provided by at least one network or application entity; determining the capability of acting as FL client for an analytics event and/ or an application data source; and registering to a service registry, wherein registering comprises providing its identification and capabilities as FL client.

[0174] There is further provided, a method (at for instance a ML model training server function) for supporting federated learning client services by an AF, the method comprising: querying at least one AF for acting as an FL participant for an analytics event (the participant can be either as data source or FL client), wherein the query can comprise the generation of trigger event; determining a requirement for FL, using at least one AF for an analytics event; and discovering information on the at least one AF, based on the determined requirement.

[0175] There is further provided, a method (at for instance, a service registry) for supporting federated learning client services by an AF, the method comprising: receiving registration information from at least one AF, wherein the registration info comprises application capability to act as FL client; storing the received registration information; receiving a request to discover the registration information related to at least one AF acting as FL client; fetching discovery information related to at least one AF acting as FL client; sending the fetched discovery information. [0176] There is further provided, a method (at for instance, an exposure function) for supporting the registration and discovery of federated learning client services, the method comprising: mapping an application identifier to at least one FL client capabilities; receiving a registration request for an external FL client; translating the request to register an external FL client based on the capabilities mapping; and sending the translated registration request to the service registry.

[0177] It should be noted that the above-mentioned methods and apparatus illustrate rather than limit the invention, and that those skilled in the art will be able to design many alternative arrangements without departing from the scope of the appended claims. The word “comprising” does not exclude the presence of elements or steps other than those listed in a claim, “a” or “an” does not exclude a plurality, and a single processor or other unit may fulfil the functions of several units recited in the claims. Any reference signs in the claims shall not be construed so as to limit their scope.

[0178] Further, while examples have been given in the context of particular communication standards, these examples are not intended to be the limit of the communication standards to which the disclosed method and apparatus may be applied. For example, while specific examples have been given in the context of 3GPP, the principles disclosed herein can also be applied to another wireless communication system, and indeed any communication system which uses routing rules.

[0179] The method may also be embodied in a set of instructions, stored on a computer readable medium, which when loaded into a computer processor, Digital Signal Processor (DSP) or similar, causes the processor to carry out the hereinbefore described methods.

[0180] The described methods and apparatus may be practiced in other specific forms. The described methods and apparatus are to be considered in all respects only as illustrative and not restrictive. The scope of the invention is, therefore, indicated by the appended claims rather than by the foregoing description. All changes which come within the meaning and range of equivalency of the claims are to be embraced within their scope.

[0181] The following abbreviations are relevant in the field addressed by this document: AF, Application Function; NF, Network Function; NWDAF, Network Data Analytics Function; OAM, Operations and Maintenance; UE, User Equipment; MDAS, Management Domain Analytics Service; AD AES, Application Data Analytics Enabler Service / Server; ANLF, Analytics Logical Function; MTLF, Model Training Logical Function; DNAI, Data Network Access Identifier; MOS, Mean Opinion Score; MDT, Minimization of Drive Tests; ADAEC, Application Data Analytics Enabler Client;

TRLF, Trusted Rating Logical Function; and ML, Machine Learning.

Claims

1. An application entity in a wireless communication system, comprising: a processor; and a memory coupled with the processor, the processor configured to cause the application entity to: receive, from at least one other network or application entity of a wireless communication system, a query for acting as a federated learning participant for a particular machine learning enabled analytics event, wherein the wireless communication system comprises a core network; determine, for the particular machine learning enabled analytics event, a federated learning client profile, wherein the federated learning client profile comprises a capability of the application entity to act as a federated learning client for at least one data source that is external to the core network, and/ or to act as a data source that is external to the core network, for the particular machine learning enabled analytics event; and transmit, to a service registry entity, a request for registering a registration information, the registration information comprising the federated learning client profile and an identifier for the application entity.

2. The application entity of claim 1, wherein the processor is configured to cause the application entity, in determining a federated learning client profile, to: determine whether a data source that is external to the core network, can be exposed to the at least one other network or application entity for the purposes of the particular machine learning enabled analytics event.

3. The application entity of claim 2, wherein the processor is further configured to cause the application entity to: transmit, to the at least one other network or application entity, an indication that machine learning using the data source that is external to the core network, can be performed at an external data network that is external to the core network.

4. The application entity of any preceding claim, wherein the query for acting as a federated learning participant, comprises a request for data for the particular machine learning enabled analytics event.

5. The application entity of any preceding claim, wherein the query for acting as a federated learning participant comprises, an indication that federated learning is to be utilized for the particular machine learning-enabled analytics event.

6. The application entity of any preceding claim, wherein the registration information comprises: an application function identifier; an application identifier; an application data analytics enabler service identifier; a user equipment identifier; an identifier for a supported analytics type; a serving area, comprising a geographical and/ or topological area; an identifier for a local data source; and/ or a preferred time period for federated learning.

7. The application entity of any preceding claim, wherein the service registry entity is a service registry entity selected from the list of service registries consisting of: a network repository function; a common application programming interface framework core function; a user data repository; an application registry; a data network registry; and an edge or cloud registry.

8. The application entity of any preceding claim, wherein the at least one other network or application entity comprises at least one network or application entity selected from the list consisting of: a network exposure function; a data analytics function; and a machine learning model training logical function.

9. A server entity in a wireless communication system, comprising a processor; and a memory coupled with the processor, the processor configured to cause the server entity to: determine a federated learning requirement for a particular machine learning enabled analytics event, wherein the federated learning requirement uses at least one application entity that is external to a core network of the wireless communication system; and transmit, to a service registry entity, a request to discover information of the at least one application entity, based on the federated learning requirement.

10. The server entity of claim 9, wherein the processor is configured to cause the server entity to: query, the at least one application entity, for acting as a federated learning participant for the particular machine learning enabled analytics event.

11. The server entity of claim 10, wherein the query for acting as a federated learning participant comprises, a request for data for the particular machine learning enabled analytics event.

12. The server entity of any one of claims 10-11, wherein the query for acting as a federated learning participant comprises, an indication that federated learning is to be utilized for the particular machine learning-enabled analytics event.

13. The server entity of any one of claims 9-12, wherein the processor is configured to cause the server entity, in determining a federated learning requirement, to: receive, from a network entity, a request for a trained machine learning model associated with the particular machine learning enabled analytics event; and determine the federated learning requirement based at least in part on the request for the trained machine learning model.

14. The server entity of claim 13, wherein the request for a trained machine learning model comprises: an identifier for the particular machine learning enabled analytics event; and a machine learning model area of interest.

15. The server entity of claim 14, wherein the request to discover information, comprises: the identifier for the particular machine learning enabled analytics event; an indication of federated learning; a time period of interest for federated learning; an indication for discovery of one or more federated learning clients for at least one data source that is external to the core network and/ or for discovery of at least one data source that is external to the core network, for the particular machine learning enabled analytics event.

16. The server entity of any one of claims 9-15, wherein the service registry entity is a service registry entity selected from the list of service registries consisting of: a network repository function; a common application programming interface framework core function; a user data repository; an application registry; a data network registry; and an edge or cloud registry.

17. The server entity of any one of claims 9-16, wherein the server entity is selected from the list of server entities consisting of: a network exposure function; a data analytics function; and a machine learning model training logical function.

18. A service registry entity in a wireless communication system, comprising: a processor; and a memory coupled with the processor, the processor configured to cause the service registry entity to: receive, from at least one application entity external to a core network of the wireless communication system, a request for registering a registration information, the registration information comprising an identity of the respective application entity and a respective federated learning client profile, wherein the federated learning client profile comprises a capability of the respective application entity to act as a federated learning client for at least one data source that is external to the core network and/ or to act as a data source that is external to the core network, for a particular machine learning enabled analytics event; and store, in the memory, the registration information.

19. A service registry entity according to claim 18, wherein the processor is further configured to cause the service registry entity to: receive, from a server entity, a request to discover information of at least one application entity acting as a federated learning client for at least one data source that is external to the core network and/ or acting as an data source that is external to the core network, for a particular machine learning enabled analytics event; fetch, from the memory, discovery information, wherein the discovery information comprises at least one of the stored registration information; and transmit the discovery information, to the server entity.

20. The service registry entity of claim 19, wherein the processor is further configured to cause the service registry entity to: authorize the request to discover information.

21. The service registry entity of any one of claims 18-20, wherein the registration information comprises: an application function identifier; an application identifier; an application data analytics enabler service identifier; a user equipment identifier; an identifier for a supported analytics type; a serving area, comprising a geographical and/ or topological area; an identifier for a local data source; and/ or a preferred time period for federated learning.

22. The service registry entity of any one of claims 18-21, wherein the service registry entity is a service registry entity selected from the list of service registries consisting of: a network repository function; a common application programming interface framework core function; a user data repository; an application registry; a data network registry; and an edge or cloud registry.

23. The service registry entity of any one of claims 18-22, wherein the processor is further configured to cause the service registry entity: store, in the memory, for each registration information, an indication that the registration information relates to an application entity that is external to the core network of the wireless communication system.

24. The service registry entity of any one of claims 18-23, wherein the processor is configured to cause the service registry entity to: transmit, to the at least one application entity, a response to the request for registering the registration information.

25. A method in an application entity, the application entity in a wireless communication system, comprising: receiving, from at least one other network or application entity of the wireless communication system, a query for acting as a federated learning participant for a particular machine learning enabled analytics event, wherein the wireless communication system comprises a core mobile network; determining, for the particular machine learning enabled analytics event, a federated learning client profile, wherein the federated learning client profile comprises a capability of the application entity to act as a federated learning client for at least one data source that is external to the core network and/ or to act as a data source that is external to the core network, for the particular machine learning enabled analytics event; and transmitting, to a service registry entity, a request for registering a registration information, the registration information comprising the federated learning client profile and an identifier for the application entity.

26. The method of claim 25, wherein the determining, for the particular machine learning enabled analytics event, a federated learning client profile, comprises: determining whether a data source that is external to the core network, can be exposed to the at least one other network or application entity for the purposes of the particular machine learning enabled analytics event.

27. The method of claim 26, further comprising: transmitting, to the at least one other network or application entity, an indication that machine learning using the data source that is external to the core network, can be performed at an external data network that is external to the core network.

28. The method of any one of claims 25-27, wherein the query for acting as a federated learning participant, comprises a request for data for the particular machine learning enabled analytics event.

29. The method of any one of claims 25-28, wherein the query for acting as a federated learning participant comprises, an indication that federated learning is to be utilized for the particular machine learning enabled analytics event.

30. The method of any one of claims 25-29, wherein the registration information comprises: an application function identifier; an application identifier; an application data analytics enabler service identifier; a user equipment identifier; an identifier for a supported analytics type; a serving area, comprising a geographical and/ or topological area; an identifier for a local data source; and/ or a preferred time period for federated learning.

31. The method of any one of claims 25-30, wherein the service registry entity is a service registry entity selected from the list of service registries consisting of: a network repository function; a common application programming interface framework core function; a user data repository; an application registry; a data network registry; and an edge or cloud registry.

32. The method of any one of claims 25-31, wherein the at least one other network or application entity comprises at least one network or application entity selected from the list consisting of: a network exposure function; a data analytics function; and a machine learning model training logical function.