Federated learning members grouping

Abstract

A first network equipment (NE) for wireless communication is described. The first NE may be capable of, operable to, or configured to receive, from a second NE, a first request for grouping one or more federated learning (FL) members associated with FL, wherein the request includes, an identity for a service and, optionally, at least one of a machine learning model identity, and an analytics identity, an identity of a task associated with the machine learning, and a set of identities associated with a set of one or more FL member, create an FL group based at least in part on the first request, output a first response indicative of the created FL group, wherein the first response includes an identity of the created FL group, and output a notification to one or more FL members of the created FL group.

Description

FEDERATED LEARNING MEMBERS GROUPINGTECHNICAL FIELD

[0001] The present disclosure relates to wireless communications, and more specifically to federated learning (FL) members grouping for Artificial Intelligence Machine Learning Enablement (AIMLE).BACKGROUND

[0002] A wireless communications system may include one or multiple network communication devices, such as network equipment (NE), supporting wireless communications for one or multiple user communication devices, which may be otherwise known as user equipment (UE), or other suitable terminology. The wireless communications system may support wireless communications with one or multiple user communication devices by utilizing resources of the wireless communication system (e.g., time resources (e.g., symbols, slots, subframes, frames, or the like) or frequency resources (e.g., subcarriers, carriers, or the like)). Additionally, the wireless communications system may support wireless communications across various radio access technologies including third generation (3G) radio access technology, fourth generation (4G) radio access technology, fifth generation (5G) radio access technology, among other suitable radio access technologies beyond 5G (e.g., sixth generation (6G)).SUMMARY

[0003] An article “a” before an element is unrestricted and understood to refer to “at least one” of those elements or “one or more” of those elements. The terms “a,” “at least one,” “one or more,” and “at least one of one or more” may be interchangeable. As used herein, including in the claims, “or” as used in a list of items (e.g., a list of items prefaced by a phrase such as “at least one of’ or “one or more of’ or “one or both of’) indicates an inclusive list such that, for example, a list of at least one of A, B, or C means A or B or C or AB or AC orBC or ABC (i.e., A and B and C). Also, as used herein, the phrase “based on” shall not be construed as a reference to a closed set of conditions. For example, an example step that is described as “based on condition A” may be based on both a condition A and a condition B without departing from the scope of the present disclosure. In other words, as used herein, the phrase “based on” shall be construed in the same manner as the phrase “based at least in part on. Further, as used herein, including in the claims, a “set” may include one or more elements.

[0004] A first NE for wireless communication is described. The first NE may be capable of, operable to, or configured to perform one or more operations as described herein. For example, the first NE may be capable of, operable to, or configured to receive, from a second NE, a first request for grouping one or more FL members associated with FL, wherein the request includes, an identity for a service and, optionally, at least one of a Machine Learning (ML) model identity, and an analytics identity, an identity of a task associated with the machine learning, and a set of identities associated with a set of one or more FL member, create an FL group based at least in part on the first request, output a first response indicative of the created FL group, wherein the first response includes an identity of the created FL group, and output a notification to one or more FL members of the created FL group.

[0005] A processor (e.g., a standalone processor chipset, or a component of a first device) for wireless communication is described. The processor may be capable of, operable to, or configured to perform one or more operations as described herein. For example, the processor may be capable of, operable to, or configured to receive, from a second NE, a first request for grouping one or more FL members associated with FL, wherein the request includes, an identity for a service and, optionally, at least one of a machine learning model identity, and an analytics identity, an identity of a task associated with the machine learning, and a set of identities associated with a set of one or more FL member, create an FL group based at least in part on the first request, output a first response indicative of the created FL group, wherein the first response includes an identity of the created FL group, and output a notification to one or more FL members of the created FL group.

[0006] A method performed or performable by a first NE for wireless communication is described. The method may include receiving, from a second NE, a first request for grouping one or more FL members associated with FL, wherein the request includes, an identity for aservice and, optionally, at least one of a machine learning model identity, and an analytics identity, an identity of a task associated with the machine learning, and a set of identities associated with a set of one or more FL member, creating an FL group based at least in part on the first request, outputting a first response indicative of the created FL group, wherein the first response includes an identity of the created FL group, and outputting a notification to one or more FL members of the created FL group

[0007] In some implementations of the first NE, the processor, and the method described herein may further be capable of, operable to, or configured to receive information associated with the set of one or more FL members, wherein the information includes one or more of an availability, a constraint, a role, or a type associated with a corresponding FL member, wherein the FL group is created based at least in part on the received information associated with the set of one or more FL members.

[0008] In some implementations of the first NE, the processor, and the method described herein may further be capable of, operable to, or configured to receive a second request for processing the FL group, wherein the second request includes the identity of the FL group, process the FL group, output a second response based at least in part on one or more of the received second request or the processed FL group, and output a notification to one or more FL members of the created FL group.

[0009] In some implementations of the first NE, the processor, and the method described herein may further be capable of, operable to, or configured to query the FL group, and determine whether an FL member is part of the FL group based at least in part on the querying.

[0010] In some implementations of the first NE, the processor, and the method described herein may further be capable of, operable to, or configured to modify the FL group based at least in part on a change in an availability or a capability of an FL member, wherein the availability is based at least in part on an availability of the FL member to participate in the FL group, and wherein the capability is based at least in part on a capability of the FL member to contribute to the task associated with the machine learning.

[0011] In some implementations of the first NE, the processor, and the method described herein may further be capable of, operable to, or configured to update the FL group by adding an FL member to the FL group or removing an FL member from the FL group.

[0012] In some implementations of the first NE, the processor, and the method described herein may further be capable of, operable to, or configured to delete the FL group.

[0013] In some implementations of the first NE, the processor, and the method described herein, the first NE is an Artificial Intelligence Machine Learning Environment (AIMLE) Server.

[0014] In some implementations of the first NE, the processor, and the method described herein, the analytics identity is an Application Data Analytics Enablement (ADAE) analytics identity.

[0015] In some implementations of the first NE, the processor, and the method described herein, the first NE is co-located with the second NE.

[0016] A second NE for wireless communication is described. The second NE may be capable of, operable to, or configured to perform one or more operations as described herein. For example, the second NE may be capable of, operable to, or configured to output, to a first NE, a first request for grouping one or more FL members associated with FL, wherein the request includes, an identity for a service and, optionally, at least one of a machine learning model identity, and an analytics Identity, an identity of a task associated with the machine learning, and a set of identities associated with a set of one or more FL member, receive a first response indicative of the created FL group, wherein the first response includes an identity of the created FL group.

[0017] A processor (e.g., a standalone processor chipset, or a component of a first device) for wireless communication is described. The processor may be capable of, operable to, or configured to perform one or more operations as described herein. For example, the processor may be capable of, operable to, or configured to output, to a first NE, a first request for grouping one or more FL members associated with FL, wherein the request includes, an identity for a service and, optionally, at least one of a machine learning model identity, and an analytics Identity, an identity of a task associated with the machine learning, and a set of identities associated with a set of one or more FL member, receive a first response indicative of the created FL group, wherein the first response includes an identity of the created FL group.

[0018] A method performed or performable by a second NE for wireless communication is described. The method may include outputting, to a first NE, a first request for groupingone or more FL members associated with FL, wherein the request includes, an identity for a service and, optionally, at least one of a machine learning model identity, and an analytics Identity, an identity of a task associated with the machine learning, and a set of identities associated with a set of one or more FL member, receiving a first response indicative of the created FL group, wherein the first response includes an identity of the created FL group.

[0019] In some implementations of the second NE, the processor, and the method described herein may further be capable of, operable to, or configured to cause the second NE to output a second request for processing the FL group, wherein the second request includes the identity of the FL group, and receive a second response based at least in part on one or more of the sent second request or a processed FL group.

[0020] In some implementations of the second NE, the processor, and the method described herein may further be capable of, operable to, or configured to cause the second NE to indicate in the second request a requirement to query the FL group to determine whether an FL member is part of the FL group.

[0021] In some implementations of the second NE, the processor, and the method described herein may further be capable of, operable to, or configured to indicate in the second request a requirement to modify the FL group based at least in part on a change in an availability or a capability of an FL member, wherein the availability is based at least in part on an availability of the FL member to participate in the FL group, and wherein the capability is based at least in part on a capability of the FL member to contribute to the task associated with the machine learning.

[0022] In some implementations of the second NE, the processor, and the method described herein may further be capable of, operable to, or configured to cause the second NE to indicate in the second request a requirement to update the FL group by adding an FL member to the FL group or removing an FL member from the FL group.

[0023] In some implementations of the second NE, the processor, and the method described herein may further be capable of, operable to, or configured to cause the second NE to indicate in the second request a requirement to delete the FL group.

[0024] In some implementations of the second NE, the second NE is a Vertical Application Layer, VAL, Server.

[0025] In some implementations, the analytics identity is an Application Data Analytics Enablement (ADAE) analytics identity.

[0026] In some implementations, the second NE is co-located with the first NE.BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 illustrates a procedure for supporting FL grouping in accordance with aspects of the present disclosure.

[0028] Figure 2 illustrates an example of a wireless communications system in accordance with aspects of the present disclosure in accordance with aspects of the present disclosure.

[0029] Figure 3 illustrates a scenario where a service consumer sends a request to an AIMLE Server to create an individual FL member support group for an FL process in accordance with aspects of the present disclosure.

[0030] Figure 4 illustrates a scenario where a service consumer sends a request to an AIMLE Server to query an individual FL member support group for an FL process in accordance with aspects of the present disclosure.

[0031] Figure 5 illustrates a scenario where a service consumer sends a request to an AIMLE Server to update an individual FL member support group for an FL process in accordance with aspects of the present disclosure.

[0032] Figure 6 illustrates a scenario where a service consumer sends a request to an AIMLE Server to modify an individual FL member support group for an FL process in accordance with aspects of the present disclosure.

[0033] Figure 7 illustrates a scenario where a service consumer sends a request to an AIMLE Server to delete an individual FL member support group for an FL process in accordance with aspects of the present disclosure.

[0034] Figure 8 illustrates a Uniform Resource Identifier (URI) structure for an AIMLES FLMemberGroupSupport Application Programming Interface (API) in accordance with aspects of the present disclosure.

[0035] Figure 9 illustrates a scenario where a service consumer sends a request to a repository to fetch information on FL member support group for an FL process in accordance with aspects of the present disclosure.

[0036] Figure 10 illustrates the resource URIs structure for an AIMLES FLMemberGroupInformation API in accordance with aspects of the present disclosure.

[0037] Figure 11 illustrates an example of a NE 1100 in accordance with aspects of the present disclosure.

[0038] Figure 12 is a flowchart illustrating a method 1200 performed by a NE in accordance with aspects of the present disclosure.DETAILED DESCRIPTION

[0039] The 3rd Generation Partnership Project (3GPP) refers to a collaborative initiative among multiple standards organizations that develop protocols for mobile telecommunications technologies. These technologies include, but are not limited to, radio access, core network functionality, and service capabilities, collectively providing a comprehensive system framework for mobile telecommunications.

[0040] The Network Data Analytics Function (NWDAF) is defined by 3GPP as a mechanism in 5G networks for collecting data from UEs, network functions (NFs), Operations, Administration, and Maintenance (0AM) systems, among others. The NWDAF may operate within the 5G Core (5GC), as well as in cloud and edge network environments, to support analytics. The NWDAF is located within the 5G core network domain and may be configured to provide data analytics that assist service providers to improve user experiences, network efficiency, and identify opportunities for new revenue generation. In some implementations, the NWDAF may expose analytics capabilities via open Application Programming Interfaces (APIs) to authorized external entities, such as content providers, streaming services, financial institutions, among others.

[0041] In some cases, the NWDAF may utilize one or more Machine Learning (ML) models, which are typically developed through an iterative process referred to as federated learning (FL). Each ML model can be identified by a corresponding model identity (ID) andmay be provided by various entities, including a network operator, a telecommunications equipment vendor, an edge service provider, or an application provider among others. The ML models may be applicable for mobile devices in the 5G system for use cases such as image recognition, localization, performance monitoring, speech recognition, video processing, and optimization of network elements or communication parameters. For example, an ML model can be trained to determine or derive UE location patterns over a specific time and geographic areas, evaluate network or cell performance for a given UE, or predict the network load (e.g., data traffic, or the like) of a network entity. On the network side, ML models may be stored at network functions serving as ML model repositories, and such models may be referenced using their respective ML model IDs. For externally provided ML models, there might be no provisioning mechanism for configuring the model ID or the location where such models are stored.

[0042] According to the 3GPP system architecture (e.g., up to Release 18), the NWDAF is configured to provide analytics outputs to one or more Analytics Consumer NFs, based on data collected from one or more Data Producer NFs. The Analytics Consumer NFs may subscribe to the NWDAF to receive analytics data.

[0043] As described above, 3 GPP specifications support FL of ML models between NWDAFs. For example, an FL Server NWDAF may provide an ML model to one or more FL Client NWDAFs, which may further train the model using locally available data. Upon completion of local training, each FL Client NWDAF may output (e.g., transmit) the updated ML model parameters or model weights back to the FL Server NWDAF. The FL Server NWDAF may then aggregate the received model updates (e.g., ML model parameters and / or model weights) to generate an updated global ML model. This process may be repeated iteratively until a target accuracy is reached or a predefined training time limit (e.g., upper bound threshold for training) is reached.

[0044] 3 GPP TS 23.482 describes a procedure for grouping of FL members as part of the Artificial Intelligence Machine Learning Enablement (AIMLE) framework. However, the procedure is limited in scope, as it primarily describes a mechanism for allowing a Vertical Application layer (VAL) Server to perform a request and response exchange with an AIMLE Server.

[0045] Figure 1 illustrates a procedure for supporting FL grouping in accordance with aspects of the present disclosure. The procedure includes one or more of a VAL Server 100, an AIMLE Server 102, an ML repository 104, and one or more FL members 106 (e.g. AIMLE clients). At step 1, the VAL Server 100 outputs (e.g., transmits) an FL member grouping support request to the AIMLE Server 102 for supporting an FL process. At step 6, the AIMLE Server 102 outputs (e.g., transmits) an FL member grouping support response to the VAL request indicating the group creation and the group information. [Further steps illustrated in Figure 1 are described below in the context of the proposed solution.] However, in the example of Figure 1, the procedure does not address operations such as creation, querying, updating, modifying, and termination of FL member groupings for AIMLE based on specific requests initiated (e.g., transmitted) by the VAL Server 100 to the AIMLE Server 102.

[0046] This is problematic as it should be possible to independently create, modify and query a group, rather than permitting creation and querying only at the time that a query is made. Currently, only a “custom” solution is possible and does not permit the use of a standard operation using HTTP POST, PUT, PATCH, etc.

[0047] Aspects of the present disclosure are described in the context of a wireless communications system.

[0048] Figure 2 illustrates an example of a wireless communications system 200 in accordance with aspects of the present disclosure. The wireless communications system 200 may include one or more NE 202, one or more UE 204, and a core network (CN) 206. The wireless communications system 200 may support various radio access technologies. In some implementations, the wireless communications system 200 may be a 4G network, such as an LTE network or an LIE -Advanced (LTE-A) network. In some other implementations, the wireless communications system 200 may be a NR network, such as a 5G network, a 5G- Advanced (5G-A) network, or a 5G ultrawideband (5G-UWB) network. In other implementations, the wireless communications system 200 may be a combination of a 4G network and a 5G network, or other suitable radio access technology including Institute of Electrical and Electronics Engineers (IEEE) 802.11 (Wi-Fi), IEEE 802.16 (WiMAX), IEEE 802.20. The wireless communications system 200 may support radio access technologies beyond 5G, for example, 6G. Additionally, the wireless communications system 200 maysupport technologies, such as time division multiple access (TDMA), frequency division multiple access (FDMA), or code division multiple access (CDMA), etc.

[0049] The one or more NE 202 may be dispersed throughout a geographic region to form the wireless communications system 200. One or more of the NE 202 described herein may be or include or may be referred to as a network node, a base station, a network element, a network function, a network entity, a radio access network (RAN), a NodeB, an eNodeB (eNB), a next-generation NodeB (gNB), or other suitable terminology. An NE 202 and a UE 204 may communicate via a communication link, which may be a wireless or wired connection. For example, an NE 202 and a UE 204 may perform wireless communication (e.g., receive signaling, transmit signaling) over a Uu interface.

[0050] An NE 202 may provide a geographic coverage area for which the NE 202 may support services for one or more UEs 204 within the geographic coverage area. For example, an NE 202 and a UE 204 may support wireless communication of signals related to services (e.g., voice, video, packet data, messaging, broadcast, etc.) according to one or multiple radio access technologies. In some implementations, an NE 202 may be moveable, for example, a satellite associated with a non-terrestrial network (NTN). In some implementations, different geographic coverage areas 112 associated with the same or different radio access technologies may overlap, but the different geographic coverage areas may be associated with different NE 202.

[0051] The one or more UE 204 may be dispersed throughout a geographic region of the wireless communications system 200. A UE 204 may include or may be referred to as a remote unit, a mobile device, a wireless device, a remote device, a subscriber device, a transmitter device, a receiver device, or some other suitable terminology. In some implementations, the UE 204 may be referred to as a unit, a station, a terminal, or a client, among other examples. Additionally, or alternatively, the UE 204 may be referred to as an Internet-of-Things (loT) device, an Internet-of-Everything (loE) device, or machine-type communication (MTC) device, among other examples.

[0052] A UE 204 may be able to support wireless communication directly with other UEs 204 over a communication link. For example, a UE 204 may support wireless communication directly with another UE 204 over a device-to-device (D2D) communication link. In some implementations, such as vehicle-to-vehicle (V2V) deployments, vehicle-to-everything(V2X) deployments, or cellular-V2X deployments, the communication link 114 may be referred to as a sidelink. For example, a UE 204 may support wireless communication directly with another UE 204 over a PC5 interface.

[0053] An NE 202 may support communications with the CN 206, or with another NE 202, or both. For example, an NE 202 may interface with other NE 202 or the CN 206 through one or more backhaul links (e.g., SI, N2, N2, or network interface). In some implementations, the NE 202 may communicate with each other directly. In some other implementations, the NE 202 may communicate with each other or indirectly (e.g., via the CN 206. In some implementations, one or more NE 202 may include subcomponents, such as an access network entity, which may be an example of an access node controller (ANC). An ANC may communicate with the one or more UEs 204 through one or more other access network transmission entities, which may be referred to as a radio heads, smart radio heads, or transmission-reception points (TRPs).

[0054] The CN 206 may support user authentication, access authorization, tracking, connectivity, and other access, routing, or mobility functions. The CN 206 may be an evolved packet core (EPC), or a 5G core (5GC), which may include a control plane entity that manages access and mobility (e.g., a mobility management entity (MME), an access and mobility management functions (AMF)) and a user plane entity that routes packets or interconnects to external networks (e.g., a serving gateway (S-GW), a Packet Data Network (PDN) gateway (P-GW), or a user plane function (UPF)). In some implementations, the control plane entity may manage non-access stratum (NAS) functions, such as mobility, authentication, and bearer management (e.g., data bearers, signal bearers, etc.) for the one or more UEs 204 served by the one or more NE 202 associated with the CN 206.

[0055] The CN 206 may communicate with a packet data network over one or more backhaul links (e.g., via an SI, N2, N2, or another network interface). The packet data network may include an application server. In some implementations, one or more UEs 204 may communicate with the application server. A UE 204 may establish a session (e.g., a protocol data unit (PDU) session, or the like) with the CN 206 via an NE 202. The CN 206 may route traffic (e.g., control information, data, and the like) between the UE 204 and the application server using the established session (e.g., the established PDU session). The PDUsession may be an example of a logical connection between the UE 204 and the CN 206 (e.g., one or more network functions of the CN 206).

[0056] In the wireless communications system 200, the NEs 202 and the UEs 204 may use resources of the wireless communications system 200 (e.g., time resources (e.g., symbols, slots, subframes, frames, or the like) or frequency resources (e.g., subcarriers, carriers)) to perform various operations (e.g., wireless communications). In some implementations, the NEs 202 and the UEs 204 may support different resource structures. For example, the NEs 202 and the UEs 204 may support different frame structures. In some implementations, such as in 4G, the NEs 202 and the UEs 204 may support a single frame structure. In some other implementations, such as in 5G and among other suitable radio access technologies, the NEs 202 and the UEs 204 may support various frame structures (i.e., multiple frame structures). The NEs 202 and the UEs 204 may support various frame structures based on one or more numerologies.

[0057] One or more numerologies may be supported in the wireless communications system 200, and a numerology may include a subcarrier spacing and a cyclic prefix. A first numerology (e.g., / r=0) may be associated with a first subcarrier spacing (e.g., 15 kHz) and a normal cyclic prefix. In some implementations, the first numerology (e.g., / r=0) associated with the first subcarrier spacing (e.g., 15 kHz) may utilize one slot per subframe. A second numerology (e.g., / r=l) may be associated with a second subcarrier spacing (e.g., 30 kHz) and a normal cyclic prefix. A third numerology (e.g., / r=2) may be associated with a third subcarrier spacing (e.g., 60 kHz) and a normal cyclic prefix or an extended cyclic prefix. A fourth numerology (e.g., / r=3) may be associated with a fourth subcarrier spacing (e.g., 120 kHz) and a normal cyclic prefix. A fifth numerology (e.g., / r=4) may be associated with a fifth subcarrier spacing (e.g., 240 kHz) and a normal cyclic prefix.

[0058] A time interval of a resource (e.g., a communication resource) may be organized according to frames (also referred to as radio frames). Each frame may have a duration, for example, a 10 millisecond (ms) duration. In some implementations, each frame may include multiple subframes. For example, each frame may include 10 subframes, and each subframe may have a duration, for example, a 1 ms duration. In some implementations, each frame may have the same duration. In some implementations, each subframe of a frame may have the same duration.

[0059] Additionally or alternatively, a time interval of a resource (e.g., a communication resource) may be organized according to slots. For example, a subframe may include a number (e.g., quantity) of slots. The number of slots in each subframe may also depend on the one or more numerologies supported in the wireless communications system 200. For instance, the first, second, third, fourth, and fifth numerologies (i.e., / r=0, jU=l, / r=2, jU=3, / r=4) associated with respective subcarrier spacings of 15 kHz, 30 kHz, 60 kHz, 120 kHz, and 240 kHz may utilize a single slot per subframe, two slots per subframe, four slots per subframe, eight slots per subframe, and 16 slots per subframe, respectively. Each slot may include a number (e.g., quantity) of symbols (e.g., OFDM symbols). In some implementations, the number (e.g., quantity) of slots for a subframe may depend on a numerology. For a normal cyclic prefix, a slot may include 14 symbols. For an extended cyclic prefix (e.g., applicable for 60 kHz subcarrier spacing), a slot may include 12 symbols. The relationship between the number of symbols per slot, the number of slots per subframe, and the number of slots per frame for a normal cyclic prefix and an extended cyclic prefix may depend on a numerology. It should be understood that reference to a first numerology (e.g., / i =0) associated with a first subcarrier spacing (e.g., 15 kHz) may be used interchangeably between subframes and slots.

[0060] In the wireless communications system 200, an electromagnetic (EM) spectrum may be split, based on frequency or wavelength, into various classes, frequency bands, frequency channels, etc. By way of example, the wireless communications system 200 may support one or multiple operating frequency bands, such as frequency range designations FR1 (410 MHz - 7.125 GHz), FR2 (24.25 GHz - 52.6 GHz), FR3 (7.125 GHz - 24.25 GHz), FR4 (52.6 GHz - 114.25 GHz), FR4a or FR4-1 (52.6 GHz - 71 GHz), and FR5 (114.25 GHz - 300 GHz). In some implementations, the NEs 202 and the UEs 204 may perform wireless communications over one or more of the operating frequency bands. In some implementations, FR1 may be used by the NEs 202 and the UEs 204, among other equipment or devices for cellular communications traffic (e.g., control information, data). In some implementations, FR2 may be used by the NEs 202 and the UEs 204, among other equipment or devices for short-range, high data rate capabilities.

[0061] FR1 may be associated with one or multiple numerologies (e.g., at least three numerologies). For example, FR1 may be associated with a first numerology (e.g., / r=0),which includes 15 kHz subcarrier spacing; a second numerology (e.g., / r=l), which includes 30 kHz subcarrier spacing; and a third numerology (e.g., / r=2), which includes 60 kHz subcarrier spacing. FR2 may be associated with one or multiple numerologies (e.g., at least 2 numerologies). For example, FR2 may be associated with a third numerology (e.g., / r=2), which includes 60 kHz subcarrier spacing; and a fourth numerology (e.g., / r=3), which include s 120 kHz subcarrier spacing.

[0062] As noted above, 3 GPP TS 23.482 provides a procedure for the grouping of the FL members using AIMLE. Such a grouping may be applicable to a specific VAL request or ML model ID or ADAE analytics ID. A grouping can also be applicable for a given service area in which one or more FL processes are expected to run. A grouping of FL members is performed in order to optimise the process of selecting and updating FL members that are entering or leaving a group.

[0063] The grouping procedure proposed here encompasses:• the creation of the FL member grouping;• a query for an individual FL Member to determine whether or not the member is part of the created group;• a modification of the group membership based on a change in the availability or capability of a FL member (e.g. due to high load or energy consumption, the FL member may have limited capability to act as FL client for a given area and time);• updating of the group due to a new member entering or an existing member leaving the FL group; and• deletion of the FL member group, and notification of the FL members regarding the deletion of the FL member group. These FL members are the members impacted by the deletion.

[0064] Referring to the signalling flow of Figure 1, this may now encompass the following procedure for FL member grouping, with the numbering corresponding to that used in the Figure:1. The VAL Server sends an FL member grouping support request to the AIMLE Server for supporting an FL process. The initial request is to create the FL member grouping support as described in Table 8.17.3.1-1, which may be followed by other requests for querying (as described in Table 8.17.3.1-2), update or modification (asdescribed in Table 8.17.3.1-3), or deletion (as described in Table 8.17.3.1-4) of the FL member grouping support.NOTE 1: The FL member grouping support request can be triggered by theAIMLE Server itself, e.g where the Vai Server is co-located with the AIMLE Server.2. The AIMLE Server, based on the request, determines the need for creating and processing a group consisting of the needed FL members for a given ML task (i.e., an ML model training / inference job ID). The need for creating an FL member group may be based on an ML task for a given AIMLE service area or for a given AIMLE service area where one or more ML tasks are expected to run, based on the step 1 request.3. To create, query, update, or modify the FL member grouping support, the AIMLE Server fetches the available FL members for the given ML task (i.e., an ML model training / inference job ID) from the ML repository. Based on this information, the AIMLE Server may select one or more FL members for the group, for the ML task.NOTE 2: If the FL member is an AIMLE client, this step re-uses procedure 8.9.2 on AIMLE client selection.4. The AIMLE Server creates, configures, and processes the FL member group based on the available or selected FL members by the aggregator, which may be the VAL Server or the AIMLE Server. The criteria for determining the group members can be the capabilities of the FL participants, or whether the candidate participants are fixed or mobile nodes and their availabilities, and the proximity of the participants to one another.5. The AIMLE Server notifies the candidate FL members (including AIMLE client if the candidate is VAL UEs) about the group ID and the group member identities for the ML model ID / analytics ID (based on the request in step 1. These are the FL members impacted by the request.NOTE 3 : If the request concerns the deletion of the FL member group, the FL member grouping indication includes notification for the deletion of the FL member group.6. The AIMLE Server sends an FL member grouping support response to the VAL request indicating the group creation or providing the query responseupdate / modification or deletion (based on the step 1 request) and the group information.

[0065] Table 8.17.3.2-1 shows the response sent by the AIMLE Server to the VAL Server for the FL member grouping procedure to create the FL member grouping support.

[0066] Table 8.17.3.2-2 shows the response sent to the VAL Server by the AIMLE Server for the FL member grouping procedure to query the FL member within the group.

[0067] Table 8.17.3.2-3 shows the response sent to the VAL Server by the AIMLE Server for the FL member grouping procedure to update or modify the FL member grouping support.

[0068] Table 8.17.3.3-4 shows the response sent to the VAL Server by the AIMLE Server for the FL member grouping procedure to delete the FL member grouping support.

[0069] Table 8.17.3.3-1 shows the notification sent by the AIMLE Server to the FL members (AIMLE clients, VAL Servers) for the FL member grouping procedure, i.e. to those FL members impacted by the grouping.

[0070] By way of further example, the following implementation details may prove helpful. These details may be considered as “Stage 3” text.Creation and handling of FL member groupThe following refers to creating, handling, and deleting FL member grouping.5.2.3 AIMLES FLMemberGroupSupport API5.2.3.1 Service DescriptionFL service allows AIMLE Server with the capability to enable creating, handling, and deleting FL member groups consisting of AIMLE clients based onAIMLES FLMemberGroupSupport service operations as defined in 3GPP TS 23.482.5.2.3.2 Service Operations5.2.3.2.1 IntroductionThe service operation defined for AIMLES FLMemberGroupSupport API for is shown in the table 5.2.3.2.1-1.5.2.3.2.2 AIMLES FLMemberGroupSupport Create5.2.3.2.2.1 GeneralThis service operation is used by a service consumer e.g., VAL Server to request the AIMLE Server to create an Individual FL Member Support Group for an FL process. The following procedure is supported by the "AIMLES FLMemberGroupSupport Create" service operation:- AIMLES FL Member Group Support Create.5.2.3.2.2.2 AIMLES FL Member Group Support CreateFigure 3 depicts a scenario where a service consumer, 300, e.g., VAL Server, sends a request to the AIMLE Server 302 to create an Individual FL Member Support Group for an FL process, (see also clause 8.17.2 of 3GPP°TS°23.482°).1. In order to create an Individual FL Member Support Group for an FL process, the service consumer e.g., VAL Server shall send an HTTP POST request to the AIMLE Server targeting the URI of the corresponding resource (i.e., "FL Member Group Support Configurations"), with the request body including the FIMbrSuppGrpReq data structure.2a. Upon success that the request to create the Individual FL Member Support Group for an FL process is successfully received and processed, the AIMLE Server shall respond with an HTTP "201 Created" status code with the request body including the FIMbrSuppGrpResp data structure.2b. On failure, the appropriate HTTP status code indicating the error shall be returned and appropriate additional error information should be returned in the HTTP POST response body, as specified in clause 6.1.3.7.5.2.3.2.3 AIMLES FLMemberGroupSupport Query5.2.3.2.3.1 GeneralThis service operation is used by a service consumer e.g., VAL Server to request the AIMLE Server to query an Individual FL Member Support Group for an FL process. The following procedure is supported by the "AIMLES FLMemberGroupSupport Query" service operation:- AIMLES FL Member Group Support Query.5.2.3.2.3.2 AIMLES FL Member Group Support QueryFigure 4 depicts a scenario where a service consumer, 400, e.g., VAL Server, sends a request to the AIMLE Server 402 to query an Individual FL Member Support Group for an FL process, (see also clause 8.17.2 of 3GPP°TS°23.482°).1. In order to query an Individual FL Member Support Group for an FL process, the service consumer e.g., VAL Server shall send an HTTP GET request to the AIMLE Server targeting the URI of the corresponding resource (i.e., "Individual FL Member Group Support Configuration").2a. Upon success that the request to query the Individual FL Member Support Group for an FL process is successfully received and processed, the AIMLE Server shall respond with an HTTP "200 OK" status code with the request body including the FIMbrSuppGrp data structure.2b. On failure, the appropriate HTTP status code indicating the error shall be returned and appropriate additional error information should be returned in the HTTP GET response body, as specified in clause 6.1.3.7.5.2.3.2.4 AIMLES FLMemberGroupSupport Update5.2.3.2.4.1 GeneralThis service operation is used by a service consumer e.g., VAL Server to request the AIMLE Server to update an Individual FL Member Support Group for an FL process.The following procedure is supported by the "AIMLES FLMemberGroupSupport Update" service operation:- AIMLES FL Member Group Support Update.5.2.3.2.4.2 AIMLES FL Member Group Support UpdateFigure 5 depicts a scenario where a service consumer, 500, e.g., VAL Server, sends a request to the AIMLE Server 502 to update an Individual FL Member Support Group for an FL process, (see also clause 8.17.2 of 3GPP°TS°23.482°).1. In order to update an Individual FL Member Support Group for an FL process, the service consumer e.g., VAL Server shall send an HTTP PUT request to the AIMLE Server targeting the URI of the corresponding resource (i.e., "Individual FL Member Group Support Configuration"), with the request body including the FIMbrSuppGrp data structure.2a. Upon success that the request to update the Individual FL Member Support Group for an FL process is successfully received and processed, the AIMLE Server shall respond with an HTTP "200 OK" status code with the request body including the FIMbrSuppGrp data structure.2b. On failure, the appropriate HTTP status code indicating the error shall be returned and appropriate additional error information should be returned in the HTTP PUT response body, as specified in clause 6.1.3.7.5.2.3.2.5 AIMLES FLMemberGroupSupport Modify5.2.3.2.5.1 GeneralThis service operation is used by a service consumer e.g., VAL Server to request the AIMLE Server to modify an Individual FL Member Support Group for an FL process.The following procedure is supported by the "AIMLES FLMemberGroupSupport Modify" service operation:- AIMLES FL Member Group Support Modify.5.2.3.2.5.2 AIMLES FL Member Group Support ModifyFigure 6 depicts a scenario where a service consumer, 600, e.g., VAL Server, sends a request to the AIMLE Server 602 to modify an Individual FL Member Support Group for an FL process, (see also clause 8.17.2 of 3GPP°TS°23.482°).1. In order to modify an Individual FL Member Support Group for an FL process, the service consumer e.g., VAL Server shall send an HTTP PATCH request to the AIMLE Server targeting the URI of the corresponding resource (i.e., "Individual FL Member Group Support Configuration"), with the request body including the FIMbrSuppGrpPatch data structure.2a. Upon success that the request to update the Individual FL Member Support Group for an FL process is successfully received and processed, the AIMLE Server shall respond with an HTTP "200 OK" status code with the request body including the FIMbrSuppGrp data structure.2b. On failure, the appropriate HTTP status code indicating the error shall be returned and appropriate additional error information should be returned in the HTTP PATCH response body, as specified in clause 6.1.3.7.5.2.3.2.6 AIMLES FLMemberGroupSupport Delete5.2.3.2.6.1 GeneralThis service operation is used by a service consumer e.g., VAL Server to request the AIMLE Server to delete an Individual FL Member Support Group for an FL process.The following procedure is supported by the "AIMLES FLMemberGroupSupport Delete" service operation:- AIMLES FL Member Group Support Delete.5.2.3.2.6.2 AIMLES FL Member Group Support DeleteFigure 7 depicts a scenario where a service consumer, 700, e.g., VAL Server sends a request to the AIMLE Server 702 to delete an Individual FL Member Support Group for an FL process, (see also clause 8.17.2 of 3GPP°TS°23.482°).1. In order to delete an Individual FL Member Support Group for an FL process, the service consumer e.g., VAL Server shall send an HTTP DELETE request to the AIMLE Server targeting the URI of the corresponding resource (i.e., "Individual FL Member Group Support Configuration").2a. Upon success that the request to delete the Individual FL Member Support Group for an FL process is successfully received and processed, the AIMLE Server shall respond with an HTTP "204 No Content" status code.2b. On failure, the appropriate HTTP status code indicating the error shall be returned and appropriate additional error information should be returned in the HTTP DELETE response body, as specified in clause 6.1.3.7.6.1.3 AIMLES FLMemberGroupSupport API6.1.3.1 IntroductionThe FL Member Group Support Service shall use the AIMLES FLMemberGroupSupport API.The API URI of the AIMLES FLMemberGroupSupport API shall be:{apiRoot} / <apiName> / <apiV ersion>The request URIs used in HTTP requests shall have the Resource URI structure defined in clause 5.2.4 of 3GPP TS 29.122, i.e.:{apiRoot} / <apiName> / <apiVersion> / <apiSpecificSuffixes> with the following components:- The {apiRoot} shall be set as described in clause 5.2.4 of 3 GPP TS 29.122.- The <apiName> shall be "aimles-fl".- The <apiVersion> shall be "vl".- The <apiSpecificSuffixes> shall be set as described in clause 5.2.4 of 3GPP TS 29.122.NOTE: When 3 GPP TS 29.122 is referenced for the common protocol and interface aspects for API definition in the clauses under clause 5, the service producer (i.e. <NF or Entity, e.g. UAE Server>) takes the role of the SCEF and the service consumer (i.e. VAL Server or AMLE Server) takes the role of the SCS / AS.6.1.3.2 Usage of HTTP and common API related aspectsThe provisions of clause 5.2 of 3GPP TS 29.122 shall apply for the AIMLES FLMemberGroupSupport API.6.1.3.3 Resources6.1.3.3.1 OverviewThis clause describes the structure for the Resource URIs and the resources and methods used for the service.Figure 8 depicts the resource URIs structure for the AIMLES FLMemberGroupSupport API.Table 6.1.3.3.1-1 provides an overview of the resources and applicable HTTP methods.AIMLES FLMemberGroupInformation5.3.X.1 Service DescriptionFL service allows AIMLE Server to fetch information on the selected FL member group based on AIMLES FLMemberGroupInformation service operations as defined in 3GPP TS 23.482.5.3.X.2Service Operations5.3.X.2.1 IntroductionThe service operation defined for AIMLES FLMemberGroupInformation API for is shown in the table 5.3.X.2.1-1.5.3. X.2.2 AIMLES FLMemberGroupInformation F etch5.3.X.2.2.1 GeneralThis service operation is used by a service consumer e.g., AIMLE Server to request the repository to fetch information on FL Member Support Group for an FL process.The following procedure is supported by the "AIMLES FLMemberGroupInformation Fetch" service operation:- AIMLES FL Member Group Information Fetch.5.3.X.2.2.2 AIMLES FL Member Group Information FetchFigure 9 depicts a scenario where a service consumer, 900, e.g., AIMLE Server, sends a request to the repository 902 to fetch information on FL Member Support Group for an FL process, (see also clause 8.17.2 of 3GPP°TS°23.482°).1. In order to fetch information on FL Member Support Group for an FL process, the service consumer e.g., AIMLE Server shall send an HTTP GET request to the repository targeting the URI of the corresponding resource (i.e., "FL Member Group Information").2a. Upon success that the request to fetch information on the FL Member Group for an FL process is successfully received and processed, the repository shall respond with an HTTP "200 OK" status code with the request body including the FIMbrSuppGrp data structure.2b. On failure, the appropriate HTTP status code indicating the error shall be returned and appropriate additional error information should be returned in the HTTP GET response body, as specified in clause 6.2.X.7.6.2.X AIMLES FLMemberGroupInformation API6.2.X. llntroductionThe FL Member Group Information Service shall use theAIMLES FLMemberGroupInformation API.The API URI of the AIMLES FLMemberGroupInformationt API shall be:{apiRoot} / <apiName> / <apiV ersion>The request URIs used in HTTP requests shall have the Resource URI structure defined in clause 5.2.4 of 3GPP TS 29.122, i.e.:{apiRoot} / <apiName> / <apiVersion> / <apiSpecificSuffixes> with the following components:- The {apiRoot} shall be set as described in clause 5.2.4 of 3 GPP TS 29.122.- The <apiName> shall be "aimles-fl-info".- The <apiVersion> shall be "vl".- The <apiSpecificSuffixes> shall be set as described in clause 5.2.4 of3GPP TS 29.122.NOTE: When 3 GPP TS 29.122 is referenced for the common protocol and interface aspects for API definition in the clauses under clause 5, the service producer (i.e. <NF or Entity, e.g. UAE Server>) takes the role of the SCEF and the service consumer (i.e. AMLE Server) takes the role of the SCS / AS.6.2.X.2Usage of HTTP and common API related aspectsThe provisions of clause 5.2 of 3GPP TS 29.122 shall apply for the AIMLES FLMemberGroupInformation API.6.2.X.3Resources6.2.X.3.1 OverviewThis clause describes the structure for the Resource URIs and the resources and methods used for the service.Figure 10 depicts the resource URIs structure for theAIMLES FLMemberGroupInformation API.Table 6.2.X.3.1-1 provides an overview of the resources and applicable HTTP methods.

[0071] Figure 11 illustrates an example of a NE 1100 in accordance with aspects of the present disclosure. The NE 1100 may include a processor 1102, a memory 1104, a controller 11011, and a transceiver 1108. The processor 1102, the memory 1104, the controller 1106, or the transceiver 1108, or various combinations thereof or various components thereof may be examples of means for performing various aspects of the present disclosure as described herein. These components may be coupled (e.g., operatively, communicatively, functionally, electronically, electrically) via one or more interfaces.

[0072] The processor 1102, the memory 1104, the controller 1106, or the transceiver 1108, or various combinations or components thereof may be implemented in hardware (e.g., circuitry). The hardware may include a processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), or other programmable logic device, or anycombination thereof configured as or otherwise supporting a means for performing the functions described in the present disclosure.

[0073] The processor 1102 may include an intelligent hardware device (e.g., a general- purpose processor, a DSP, a CPU, an ASIC, an FPGA, or any combination thereof). In some implementations, the processor 1102 may be configured to operate the memory 1104. In some other implementations, the memory 1104 may be integrated into the processor 1102. The processor 1102 may be configured to execute computer-readable instructions stored in the memory 1104 to cause the NE 1100 to perform various functions of the present disclosure.

[0074] The memory 1104 may include volatile or non-volatile memory. The memory 1104 may store computer-readable, computer-executable code including instructions when executed by the processor 1102 cause the NE 1100 to perform various functions described herein. The code may be stored in a non-transitory computer-readable medium such the memory 1104 or another type of memory. Computer-readable media includes both non- transitory computer storage media and communication media including any medium that facilitates transfer of a computer program from one place to another. A non-transitory storage medium may be any available medium that may be accessed by a general-purpose or specialpurpose computer.

[0075] In some implementations, the processor 1102 and the memory 1104 coupled with the processor 1102 may be configured to cause the NE 1100 to perform one or more of the functions described herein (e.g., executing, by the processor 1102, instructions stored in the memory 1104). For example, the processor 1102 may support wireless communication at the NE 1100 in accordance with examples as disclosed herein. The NE 1100, referred to as a first NE, may be configured to support a means for receiving, from a second NE, a first request for grouping one or more FL members associated with FL, wherein the request includes, an identity for a service and, optionally, at least one of a machine learning model identity, and an analytics identity, an identity of a task associated with the machine learning, and a set of identities associated with a set of one or more FL member, creating an FL group based at least in part on the first request, output a first response indicative of the created FL group, wherein the first response includes an identity of the created FL group, and outputting a notification to one or more FL members of the created FL group.

[0076] Alternatively, the NE 1100, referred to as a second NE, may be configured to support a means for outputting, to a first NE, a first request for grouping one or more FL members associated with FL, wherein the request includes, an identity for a service and, optionally, at least one of a machine learning model identity, and an analytics Identity, an identity of a task associated with the machine learning, and a set of identities associated with a set of one or more FL member, and receiving a first response indicative of the created FL group, wherein the first response includes an identity of the created FL group.

[0077] The controller 1106 may manage input and output signals for the NE 1100. The controller 1106 may also manage peripherals not integrated into the NE 1100. In some implementations, the controller 1106 may utilize an operating system such as iOS®, ANDROID®, WINDOWS®, or other operating systems. In some implementations, the controller 1106 may be implemented as part of the processor 1102.

[0078] In some implementations, the NE 1100 may include at least one transceiver 1108. In some other implementations, the NE 1100 may have more than one transceiver 1108. The transceiver 1108 may represent a wireless transceiver. The transceiver 1108 may include one or more receiver chains 1110, one or more transmitter chains 1112, or a combination thereof.

[0079] A receiver chain 1110 may be configured to receive signals (e.g., control information, data, packets) over a wireless medium. For example, the receiver chain 1110 may include one or more antennas for receive the signal over the air or wireless medium. The receiver chain 1110 may include at least one amplifier (e.g., a low-noise amplifier (LN A)) configured to amplify the received signal. The receiver chain 1110 may include at least one demodulator configured to demodulate the receive signal and obtain the transmitted data by reversing the modulation technique applied during transmission of the signal. The receiver chain 1110 may include at least one decoder for decoding the processing the demodulated signal to receive the transmitted data.

[0080] A transmitter chain 1112 may be configured to generate and transmit signals (e.g., control information, data, packets). The transmitter chain 1112 may include at least one modulator for modulating data onto a carrier signal, preparing the signal for transmission over a wireless medium. The at least one modulator may be configured to support one or more techniques such as amplitude modulation (AM), frequency modulation (FM), or digital modulation schemes like phase-shift keying (PSK) or quadrature amplitude modulation(QAM). The transmitter chain 1112 may also include at least one power amplifier configured to amplify the modulated signal to an appropriate power level suitable for transmission over the wireless medium. The transmitter chain 1112 may also include one or more antennas for transmitting the amplified signal into the air or wireless medium.

[0081] Figure 12 illustrates a flowchart of a method in accordance with aspects of the present disclosure. The operations of the method may be implemented by a NE as described herein. In some implementations, the NE may execute a set of instructions to control the function elements of the NE to perform the described functions.

[0082] At 1202, the method may include receiving, from a second NE, a first request for grouping one or more FL members associated with FL, wherein the request includes, an identity for a service and, optionally, at least one of a machine learning model identity, and an analytics identity, an identity of a task associated with the machine learning, and a set of identities associated with a set of one or more FL member. In some implementations, aspects of the operations of 1202 may be performed by a NE as described with reference to Figure 11.

[0083] At 1204, the method may include creating an FL group based at least in part on the first request. In some implementations, aspects of the operations of 1204 may be performed by a NE as described with reference to Figure 11.

[0084] At 1206, the method may include outputting a notification to one or more FL members of the created FL group. In some implementations, aspects of the operations of 1206 may be performed by a NE as described with reference to Figure 11.

[0085] It should be noted that the method described herein describes a possible implementation, and that the operations and the steps may be rearranged or otherwise modified and that other implementations are possible.

[0086] It should be noted that the method described herein describes a possible implementation, and that the operations and the steps may be rearranged or otherwise modified and that other implementations are possible.

[0087] The description herein is provided to enable a person having ordinary skill in the art to make or use the disclosure. Various modifications to the disclosure will be apparent to a person having ordinary skill in the art, and the generic principles defined herein may be applied to other variations without departing from the scope of the disclosure. Thus, thedisclosure is not limited to the examples and designs described herein but is to be accorded the broadest scope consistent with the principles and novel features disclosed herein.Table 8.17.3.1-1: FL member grouping support create requestTable 8.17.3.1-2: FL member grouping support query requestTable 8.17.3.1-3: FL member grouping support change requestTable 8.17.3.1-4: FL member grouping support delete requestTable 8.17.3.2-1: FL member grouping support create responseTable 8.17.3.2-2: FL member grouping support query requestTable 8.17.3.2-3: FL member grouping support change responseTable 8.17.3.3-4: FL member grouping support delete responseTable 8.17.3.3-1: FL grouping indicationTable 5.2.3.2.1-1: Operations for AIMLES FLMemberGroupSupport APITable 6.1.3.3.1-1: Resources and methods overviewTable 5.3.X.2.1-1: Operations for AIMLES FLMemberGroupInformation APITable 6.2.X.3.1-1: Resources and methods overview

Claims

CLAIMS1. A first network equipment for wireless communication comprising: at least one memory; and at least one processor coupled with the at least one memory and configured to cause the first network equipment to: receive, from a second network equipment, a first request for grouping one or more federated learning (FL) members associated with FL, wherein the request includes, an identity for a service and, optionally, at least one of a machine learning model identity, and an analytics identity, an identity of a task associated with the machine learning, and a set of identities associated with a set of one or more FL member, create an FL group based at least in part on the first request; output a first response indicative of the created FL group, wherein the first response includes an identity of the created FL group; and output a notification to one or more FL members of the created FL group.

2. The first network equipment of claim 1, wherein the at least one processor is further configured to cause the first network equipment to: receive information associated with the set of one or more FL members, wherein the information includes one or more of an availability, a constraint, a role, or a type associated with a corresponding FL member, wherein the FL group is created based at least in part on the received information associated with the set of one or more FL members.

3. The first network equipment of claim 1 or 2, wherein the at least one processor is further configured to cause the first network equipment to: receive a second request for processing the FL group, wherein the second request includes the identity of the FL group; process the FL group;output a second response based at least in part on one or more of the received second request or the processed FL group; and output a notification to one or more FL members of the created FL group, and which have been impacted by the second request.

4. The first network equipment of claim 3, wherein, to process the FL group, the at least one processor is configured to cause the first network equipment to: query the FL group; and determine whether an FL member is part of the FL group based at least in part on the querying.

5. The first network equipment of claim 3, wherein, to process the FL group, the at least one processor is configured to cause the first network equipment to: modify the FL group based at least in part on a change in an availability or a capability of an FL member, wherein the availability is based at least in part on an availability of the FL member to participate in the FL group; and wherein the capability is based at least in part on a capability of the FL member to contribute to the task associated with the machine learning.

6. The first network equipment of claim 3, wherein, to process the FL group, the at least one processor is configured to cause the first network equipment to: update the FL group by adding an FL member to the FL group or removing an FL member from the FL group.

7. The first network equipment of claim 3, wherein, to process the FL group, the at least one processor is configured to cause the first network equipment to: delete the FL group.

8. The first network equipment of any of the preceding claims, wherein the first network equipment is an Artificial Intelligence Machine Learning Environment (AIMLE) Server.

9. The first network equipment of any of the preceding claims, wherein the analytics identity is an Application Data Analytics Enablement (ADAE) analytics identity.

10. The first network equipment of any of the preceding claims, wherein the first network equipment is co-located with the second network equipment.

11. A second network equipment for wireless communication comprising: at least one memory; and at least one processor coupled with the at least one memory and configured to cause the second network equipment to: output, to a first network equipment, a first request for grouping one or more federated learning (FL) members associated with FL, wherein the request includes, an identity for a service and, optionally, at least one of a machine learning model identity, and an analytics identity, an identity of a task associated with the machine learning, and a set of identities associated with a set of one or more FL member, receive a first response indicative of the created FL group, wherein the first response includes an identity of the created FL group.

12. The second network equipment of claim 11, wherein the at least one processor is further configured to cause the second network equipment to: output a second request for processing the FL group, wherein the second request includes the identity of the FL group; and receive a second response based at least in part on one or more of the outputted second request or a processed FL group.

13. The first network equipment of claim 12, wherein the at least one processor is configured to cause the second network equipment to indicate in the second request a requirement to: query the FL group to determine whether an FL member is part of the FL group.

14. The first network equipment of claim 12, wherein the at least one processor is configured to cause the second network equipment to indicate in the second request a requirement to: modify the FL group based at least in part on a change in an availability or a capability of an FL member, wherein the availability is based at least in part on an availability of the FL member to participate in the FL group, and wherein the capability is based at least in part on whether the FL member is capable to contribute to the task associated with the machine learning.

15. The second network equipment of claim 12, wherein the at least one processor is configured to cause the second network equipment to indicate in the second request a requirement to: update the FL group by adding an FL member to the FL group or removing an FL member from the FL group.

16. The second network equipment of claim 12, wherein the at least one processor is configured to cause the second network equipment to indicate in the second request a requirement to: delete the FL group.

17. The second network equipment of any of claims 11 to 16, wherein the second network equipment is a Vertical Application Layer (VAL) Server.

18. The first network equipment of any of claims 11 to 17, wherein the analytics identity is an Application Data Analytics Enablement (ADAE) analytics identity.

19. The first network equipment of any of claims 11 to 18, wherein the second network equipment is co-located with the first network equipment.

20. A method performed by a first network equipment, the method comprising: receiving, from a second network equipment, a first request for grouping one or more federated learning (FL) members associated with FL, wherein the request includes, an identity for a service and, optionally, at least one of a machine learning model identity, and an analytics identity, an identity of a task associated with the machine learning, and a set of identities associated with a set of one or more FL member, creating an FL group based at least in part on the first request; outputting a first response indicative of the created FL group, wherein the first response includes an identity of the created FL group; and outputting a notification to one or more FL members of the created FL group.

Images