Registration and discovery to support hierarchical aimle service

Abstract

According to an aspect, there is provided a method performed by a first node in a communication network. The first node is for use in a hierarchical Artificial Intelligence Machine Learning (AIML) Enablement (AIMLE) service. The method comprises: sending (1002), to a second node in the communication network, a request to register the first node in a repository node.

Description

[0001] Registration and Discovery to Support Hierarchical AIMLE Service

[0002] TECHNICAL FIELD

[0003] This disclosure relates to Hierarchical Artificial Intelligence (Al) / Machine Learning (ML) Enablement (AIMLE) services.

[0004] BACKGROUND

[0005] Application layer support for Artificial Intelligence (Al) / Machine Learning (ML) services (AIMLAPP) has been studied in SA6 Release 19, in particular in 3rdGeneration Partnership Project (3GPP) Technical Report (TR) 23.700-82 (v19.1.0) " Study on application layer support for AI / ML services” (https: / / www.3gpp.org / ftp / Specs / archive / 23_series / 23.700-82 / 23700-82-j10.zip) and 3GPP Technical Standard (TS) 23.482 (v19.0.0) " Functional architecture and information flows for AIML Enablement Service” (https: / / www.3gpp.org / ftp / Specs / archive / 23_series / 23.482 / 23482-j00.zip).

[0006] Recently, a new Release 20 SA6 Study Item Description (SID) was approved on SA#107 plenary meeting, to continue the study of application enablement for AI / ML service (AIMLAPP_Ph2). The study item is SP-250384 " New SID on application enablement for AI / ML service Phase 2” (https: / / www.3gpp.org / ftp / Meetings_3GPP_Sync / SA / lnbox / SP-250384.zip). One of the study aspects agreed in the SID is " Identify the impacts and study potential enhancements for supporting AIML Enablement (AIMLE) services assuming diverse (e.g. hierarchical and distributed) AIMLE deployments”.

[0007] Different deployment models for AIMLE server are introduced in Release 19 AIMLAPP work. The details are given in the Annex A of 3GPP TS 23.482 v19.0.0.

[0008] Deployment scenarios (Corresponding to Annex A in 3GPP TS 23.482)

[0009] 1. General (Corresponding to A.1 in 3GPP TS 23.482)

[0010] This Annex provides the different deployment models for AIMLE services. There could be three deployment options:

[0011] AIMLE server can be deployed at a centralized cloud platform and collect data from multiple Edge Data Networks (ED Ns).

[0012] AIMLE server can be deployed at the edge platform.

[0013] Hierarchical AIMLE server deployment, where multiple AIML enablement services are deployed in edge or central clouds (e.g. in hierarchical architecture). Such deployment allows for local-global analytics for system wide optimization.

[0014] 2. Deployment model #1: Cloud-deployed AIMLE server (Corresponding to A.2 in 3GPP TS 23.482)

[0015] In this deployment, the AIMLE server is centrally located and can provide support for AIML operations to theapplication and edge services (Edge Application Server (EAS) / Edge Enabler Server (EES), Vertical Application Layer (VAL) server). An example deployment option for AIMLE server at the cloud is shown in Fig. 1.

[0016] 3. Deployment model #2: Edge-deployed AIMLE server (Corresponding to A.3 in 3GPP TS 23.482)

[0017] In this deployment, the AIMLE server is located at the EDN as EAS and provides AIML enablement services to the other EAS(s) or other edge native applications at the edge platform. AIMLE services can be deployed by the Edge Computing Service Provider (ECSP) or the Mobile Network Operator (MNO) to provide value-add services related to AI / ML operations.

[0018] The ML support operations, that the edge deployed AIMLE Server provides, are applicable to the AIMLE service areas (as shown in the example deployment scenario in Fig. 2), which are equivalent to the EDN service areas.

[0019] NOTE: AIMLE server deployed as EAS can provide application enablement service to EES.

[0020] 4. Deployment model #3: Hierarchical AIMLE server deployment (Corresponding to A.4 in 3GPP TS 23.482) In this deployment, multiple AIMLE servers can be located at different EDNs / Data Networks (DNs) and can be deployed by the same provider. Such hierarchical deployments allow the local - global ML operations (e.g. federated learning across domains).

[0021] The ML support services that the edge deployed AIMLE server correspond to the AIMLE service areas (as shown in the example in Fig. 3), which is equivalent to the EDN service areas. The central AIMLE server covers all Public Land Mobile Network (PLMN) area and is used to coordinate the ML related operations (e.g. Federated Learning (FL) server / aggregator) with the distributed AIMLE servers.

[0022] The hierarchical AIMLE deployment is used for assisting hierarchical computing as described in clause 8.25 of 3GPP TS 23.482.

[0023] Support of AIML Services for Assisting Hierarchical Computing (Corresponding to clause 8.25 of 3GPP TS 23.482) This clause describes procedure for supporting AIML services for assisting hierarchical computing.

[0024] 1. General

[0025] This clause describes the procedure for assisting hierarchical computing by the AIMLE server. An entity, e.g. Cloud Application Server (CAS) or EAS - which are defined in 3GPP TS 23.558 (v19.4.0) " Architecture for enabling Edge Applications” (https: / / www.3gpp.org / ftp / Specs / archive / 23_series / 23.558 / 23558-j40.zip) - can have different roles in hierarchical computing (with one root node (e.g. CAS, EAS), the root has one or more children which are also known as sub-root node(s) (e.g. EAS), and multiple leaf nodes (e.g. EAS) with no children). Here, hierarchical computing represents a computation architecture with multiple computation entities involved and multiple levels of computations for a computation task.2. Procedure for assisting hierarchical computing process

[0026] Fig. 4 illustrates the procedures for AIMLE server to assist a hierarchical computing process.

[0027] Pre-conditions:

[0028] 1. An AI / ML task be treated as a special computing task being completed at consumer (e.g. CAS, EAS).

[0029] 2. The consumer decides its role in the hierarchical computing architecture for an AI / ML task (e.g. FL training) based on its local configuration.

[0030] 3. The AIMLE server can assist a hierarchical computing process by providing time window(s) recommendation for computing task distribution if the consumer is a root node in a hierarchical computing process, providing time window(s) recommendation for intermediate output delivery if the consumer is a leaf node in a hierarchical computing process, and candidate execution node list provisioning or computing preparation status provisioning, etc.

[0031] 4. The consumer decides that assistance from AIMLE server to support the hierarchical computing process (AI / ML task) is needed, due to lack of capability on, e.g., execution node selection.

[0032] Fig. 4 illustrates the procedure for AIMLE servers to assist a hierarchical computing process. The corresponding procedure in detail is as follows:

[0033] 1. The VAL server (e.g. CAS, EAS) sends hierarchical computing assistance request to the edge AIMLE server for a hierarchical computing process (AI / ML task). The request message includes information as described in Table 8.25.3.1-1 (in 3GPP TS 23.482).

[0034] 2. The edge AIMLE server authenticates and authorizes the request from the consumer and checks its capability to provide the requested assistance information.

[0035] If the request is authorized and the edge AIMLE server can generate the required assistance information (e.g. computing preparation status at an execution node which is registered to it), it performs step 3 and 4.

[0036] If the request is authorized but the edge AIMLE server cannot generate the required assistance information (e.g. execution nodes are registered to different edge AIMLE servers), it performs step 5 and skips steps 3 and 4.

[0037] 3. The edge AIMLE server performs operations to generate assistance information which is requested in step 1. For example, for computing preparation status at an execution node, the edge AIMLE server may subscribe / request analytics from Application Data Analytics Enablement (ADAE) server (e.g. edge load analytics, edge computing preparation analytics) and aggregate the information received to generate assistance information.

[0038] 4. The edge AIMLE server sends hierarchical computing assistance response to the consumer (e.g.

[0039] computing preparation status at the execution node). The response message contains the information as described in Table 8.25.3.2-1 (in 3GPP TS 23.482).5. If the edge AIMLE server cannot generate the required assistance information, it sends hierarchical computing assistance request to central AIMLE server. The request message includes information as described in Table 8.25.3.1-1 (in 3GPP TS 23.482).

[0040] 6. The central Al MLE server authenticates and authorizes the request from the edge Al MLE server. 7. If the request is authorized, the central AIMLE server performs operations to generate assistance information which is requested in step 1.

[0041] For example, for execution node selection, according to the role of the VAL server in request message in step 1, the central AIMLE server derives the requirements on the execution node (e.g. high computation capability, high communication capability, or both). Then, the central AIMLE server may subscribe / request analytics from ADAE server (e.g. edge load analytics, edge computing preparation analytics), trigger generation of split operation assistance information, retrieve FL member information from ML Repository (the FL member with EAS ID). The existing services can be reused for execution node selection, e.g., the step 3 in clause 8.12.2 (in 3GPP TS 23.482).

[0042] 8. The central AIMLE server sends hierarchical computing assistance response with the generated assistance information (e.g. a list of selected candidate execution nodes). The response message contains the information as described in Table 8.25.3.2-1 (in 3GPP TS 23.482).

[0043] 8a. The central AIMLE server sends the hierarchical computing assistance response to the edge AIMLE server.

[0044] 8b. The edge AIMLE server sends the hierarchical computing assistance response to the consumer.

[0045] The VAL server (e.g. CAS, EAS) uses the assistance information for decision making on its computing operations.

[0046] NOTE: If the VAL server (e.g. CAS, EAS) knows the information of the central AIMLE server, it can send the hierarchical computing assistance request to the central AIMLE server directly for the hierarchical computing process (AI / ML task). The procedure is the same as the steps 5-8a in Fig. 4 with replacing edge AIMLE server by consumer.

[0047] SUMMARY

[0048] There currently exist certain challenge(s). For example, how to support AIMLE services assuming hierarchical AIMLE deployments is missing. For example, registration and discovery of an AIMLE server / client with AIMLE capability considering hierarchical AIMLE server deployments are not contained in the existing mechanisms.

[0049] Certain aspects of the disclosure and their embodiments may provide solutions to these or other challenges. In particular, this disclosure provides enhancements to the mechanisms on registration and discovery of a network entity (e.g. a Al MLE server / client) to support Al MLE services with a hierarchical Al MLE server deployment. Both a centralized and distributed ML Repository (entity for AIMLE server / client to register AIML capability information) can be considered for the enhancements. Furthermore, scenarios with and without direct connections between ML repositories are considered.According to a first aspect, there is provided a method performed by a first node in a communication network. The first node is for use in a hierarchical Artificial Intelligence Machine Learning, AIML, Enablement, AIMLE, service. The method comprises sending, to a second node in the communication network, a request to register the first node in a repository node.

[0050] According to a second aspect, there is provided another method performed by a first node in a communication network. The first node is for use in a hierarchical Artificial Intelligence Machine Learning, AIML, Enablement, AIMLE, service. The method comprises sending, to a second node in the communication network, a request to discover one or more clients and / or servers to participate in AIML operations.

[0051] According to a third aspect, there is provided a method performed by a second node in a communication network. The second node is for use in a hierarchical Artificial Intelligence Machine Learning, AIML, Enablement, AIMLE, service. The method comprises receiving, from a first node in the communication network, a request to register the first node in a repository node.

[0052] According to a fourth aspect, there is provided a method performed by a second node in a communication network. The second node is for use in a hierarchical Artificial Intelligence Machine Learning, AIML, Enablement, AIMLE, service. The method comprises receiving, from a first node in the communication network, a request to discover one or more clients and / or servers to participate in AIML operations.

[0053] According to a fifth aspect, there is provided a computer program product comprising a computer readable medium having computer readable code embodied therein, the computer readable code being configured such that, on execution by a suitable computer or processor, the computer or processor is caused to perform the method according to the first aspect, the second aspect, the third aspect, the fourth aspect, or any embodiments thereof.

[0054] According to a sixth aspect, there is provided a node configured to perform the method according to the first aspect, the second aspect, the third aspect, the fourth aspect, or any embodiments thereof.

[0055] According to a seventh aspect, there is provided a node comprising a processor and a memory, said memory containing instructions executable by said processor whereby said node is operative to perform the method according to the first aspect, the second aspect, the third aspect, the fourth aspect, or any embodiments thereof.

[0056] BRIEF DESCRIPTION OF THE DRAWINGS

[0057] Some of the embodiments contemplated herein will now be described more fully with reference to the accompanying drawings, in which:

[0058] Fig. 1 shows an example deployment for AIMLE at the cloud;

[0059] Fig. 2 shows another example deployment for AIMLE at the cloud;

[0060] Fig. 3 shows an exemplary hierarchical deployment of AIMLE;

[0061] Fig. 4 is a signalling diagram illustrating a procedure for assisting a hierarchical computing process;

[0062] Fig. 5 illustrates a Centralized ML Repository;Fig. 6 illustrates a Distributed ML Repository without direct connections between ML repositories;

[0063] Fig. 7 illustrates a Distributed ML Repository with direct connections between ML repositories;

[0064] Fig. 8 is a signalling diagram illustrating AIMLE Server / Client Registration;

[0065] Fig. 9 is a signalling diagram illustrating AIMLE Server / Client Discovery;

[0066] Fig. 10 is a flow chart illustrating a method performed by a first node in accordance with some embodiments; Fig. 11 is a flow chart illustrating another method performed by a first node in accordance with some embodiments;

[0067] Fig. 12 is a flow chart illustrating a method performed by a second node in accordance with some embodiments; Fig. 13 is a flow chart illustrating another method performed by a second node in accordance with some embodiments;

[0068] Fig. 14 shows an example of a communication system in accordance with some embodiments;

[0069] Fig. 15 is a block diagram illustrating a virtualization environment in which functions implemented by some embodiments may be virtualized; and

[0070] Fig. 16 shows a core network node in accordance with further embodiments.

[0071] DETAILED DESCRIPTION

[0072] Some of the embodiments contemplated herein will now be described more fully with reference to the accompanying drawings. Embodiments are provided by way of example to convey the scope of the subject matter to those skilled in the art. Additional information may also be found in the document(s) provided in the Appendix.

[0073] The term "central AIMLE server / client” refers to a AIMLE server / client that is deployed at a centralized Data Network (DN). The term "edge AIMLE server / client” refers to a AIMLE server / client is deployed at an edge DN.

[0074] Fig. 5 illustrates a Centralized ML Repository. The central AIMLE server and edge AIMLE server register to the centralized ML repository with their respective AIMLE server profiles.

[0075] An AIMLE client registers to the centralized ML repository via the central AIMLE server or the edge AIMLE server with its AIMLE client profile.

[0076] The AIMLE client, central AIMLE server, and edge AIMLE server can update their profiles in the centralized ML repository.

[0077] A consumer (e.g. a VAL server / client, other AIMLE server / client) can request discovery of AIMLE server / client for different purposes on AIML applications / operations from the central or edge AIMLE server. The central or edge AIMLE server then interact with the centralized ML repository to complete the discovery process.

[0078] Fig. 6 illustrates a Distributed ML Repository, where there are no direct connections between ML repositories. All access to the ML repository must be via an AIMLE server. In this distributed ML repository implementation, the central AIMLE server registers to the central ML repository with its AIMLE server profile, and the edge AIMLE server registers to the edge ML repository with its AIMLE server profile. An AIMLE client registers to the central or edge MLrepository via the central AIMLE server or the edge AIMLE server. The edge ML repository may share its stored information with the central ML repository via AIMLE servers as shown in Fig. 6.

[0079] A consumer (e.g. VAL server / client, other AIMLE server / client) can request discovery of AIMLE server / client for different purposes on Al ML applications / operations from the central or edge AIMLE server. If a central AIMLE server receives the discovery request, the central AIMLE server can interact with the central ML repository for the discovery. If an edge AIMLE server receives the discovery request, the edge AIMLE server can interact with its serving ML repository for the discovery. If the required information is available at the edge ML repository, the ML repository can respond to the discovery request to the consumer via the edge Al MLE server. If the required information is not available at the edge ML repository, the edge ML repository can interact with the central ML repository for the request discovery via the AIMLE servers as shown in Fig. 6. The central ML repository can respond to the discovery request to the consumer via the central and edge AIMLE servers.

[0080] Fig. 7 illustrates a Distributed ML Repository with direct connections between ML repositories. As shown in Fig.

[0081] 7, Edge ML Repositories and a Central ML repository can interact with each other without the interactions being via AIMLE servers.

[0082] Here, the central AIMLE server can register to the central ML repository with its AIMLE server profile, and the edge AIMLE server(s) register to a respective edge ML repository with its AIMLE server profile. An AIMLE client registers to the central or edge ML repository via a central AIMLE server or edge AIMLE server. An edge ML repository may share its stored information with the central ML repository.

[0083] A consumer (e.g. VAL server / client, other AIMLE server / client) can request discovery of an AIMLE server / client for different purposes on AIML applications / operations from the central or edge AIMLE server.

[0084] If a central AIMLE server receives the discovery request, the central AIMLE server can interact with the central ML repository for the discovery. If an edge AIMLE server receives the discovery request, the edge AIMLE server can interact with its serving ML repository for the discovery. If the required information is available at the edge ML repository, the ML repository can respond to the discovery request to the consumer via the edge AIMLE server. If the required information is not available at the edge ML repository, the ML repository can interact with the central ML repository for the request discovery as shown in Fig. 7. The central ML repository can respond to the discovery request to the consumer via the edge ML repository and the edge AIMLE server.

[0085] The following description provides exemplary procedures that include enhancements to the existing mechanisms on registration and discovery of AIMLE server / client to support AIMLE services with hierarchical AIMLE server deployment. Several different scenarios are considered, i.e. centralized ML Repository, and distributed ML Repository with and without direct connections between ML repositories, as introduced above and illustrated in Figs.

[0086] 5-7.

[0087] Fig. 8 illustrates the registration of an AIMLE Server / Client according to embodiments of the techniques described herein, and Fig. 9 illustrates the discovery of an AIMLE Server / Client according to embodiments of thetechniques described herein. Descriptions of these figures are provided below, and shorthand notation is used to indicate whether certain signals, signal content, or steps are applicable to the centralized ML Repository scenario, applicable to either or both of the distributed ML Repository scenarios, or common to all scenarios. For completeness, it is noted that the absence of any of the shorthand notations below indicates that the relevant signal, signal content or step applies to all scenarios.

[0088] The shorthand notation below is used to refer to the different scenarios as follows:

[0089] CMR: Centralized ML Repository (as illustrated in Fig. 5)

[0090] DMR-nD: Distributed ML Repository without direct connections between ML repositories (as illustrated in Fig.

[0091] 6)

[0092] DMR-D: Distributed ML Repository with direct connections between ML repositories (as illustrated in Fig. 7) COM: This notation is used to indicate that it relates to all three of the above scenarios.

[0093] AIMLE Server / Client Registration

[0094] Fig. 8 illustrates the registration of an AIMLE Server / Client according to embodiments of the techniques described herein. That is, both AIMLE servers and AIMLE clients need to perform respective registration procedures to register to a ML repository, and AIMLE server / client 802 in Fig. 8 represents the entity (i.e. AIMLE server or AIMLE client) that is performing the registration procedure.

[0095] The AIMLE Server / Client Registration procedure can be as follows when there are AIMLE services with a hierarchical AIMLE server deployment. In Fig. 8 the AIMLE Server 804 can be a Central AIMLE server or an Edge AIMLE server, depending on the specific hierarchical AIMLE server deployment, and likewise the ML repository 806 can be a Central ML Repository or an Edge ML Repository.

[0096] Specifically, in a CMR deployment, the AIMLE server / client 802 is an AIMLE server or AIMLE client, and AIMLE server 804 is a Central or Edge AIMLE server. In a DMR-D deployment, the AIMLE server / client 802 is an AIMLE server or an AIMLE client, the AIMLE server 804 is a Central or Edge AIMLE server, and the ML Repository 806 is a Central or Edge ML Repository as appropriate based on whether the AIMLE server 804 is a Central or Edge AIMLE server. In a DMR-nD deployment, the AIMLE server / client 802 can be an AIMLE server or AIMLE client, with the AIMLE server 804 being a Central or Edge AIMLE server, and the ML Repository 806 can be a Central or Edge ML Repository as appropriate for whether the AIMLE server 804 is a Central or Edge AIMLE server. Also in a DMR-nD deployment, the AIMLE server / client 802 can be an " Edge AIMLE server”, with the AIMLE server 804 being a Central AIMLE server, and the ML Repository 806 is a Central ML Repository.

[0097] AIMLE Registration Request (811) - The AIMLE server / client 802 sends an AIMLE registration request 811 to the (central or edge) AIMLE server 804. Besides the parameters given in Table 8.7.3.2-1 of 3GPP TS 23.48, the registration request sent by an AIMLE server 802 may include any or all of:

[0098] [COM] Data Network Name (DNN) and Data Network Access Identifier(s) (DNAI(s)) that identify in whichEDN or DN the AIMLE server 802 is located.

[0099] [COM] AIMLE server profile: information about the capability of the AIMLE server 802 to support AI / ML operations for VAL services identifies (ID(s)).

[0100] The AIMLE server profile may contain AIMLE server capability (e.g. compute capability, communication capability with AIMLE clients, etc.), supported Al ML model types, supported Al ML operations, etc. [COM] Supported role in Al ML task topology (e.g. allow be connected in a hierarchical or distributed architecture, or not allow).

[0101] [DMR-nD, DMR-D] EAS ID: identifier of the EAS which has AIMLE server deployed.

[0102] [DMR-nD, DMR-D] AIMLE server ID: the identifier of the AIMLE

[0103] Besides the parameters given in Table 8.7.3.2-1 of 3GPP TS 23.482, the registration request sent by an AIMLE client 802 may include any or all of:

[0104] [COM] DNN and DNAI(s) that identify in which EDN or DN the AIMLE client 802 is located. [COM] Besides the parameters given in Table 8.7.3.2-2 of 3GPP TS 23.482, the AIMLE client profile may include: EAS ID(s) (with AIMLE server deployed) or AIMLE server ID(s) that are serving the AIMLE client 802.

[0105] [COM] Supported role in Al ML task topology (e.g. allow be connected in a hierarchical or distributed architecture, or not allow)

[0106] Repository information sharing (811a) - although not shown in Fig. 8, in a DMR-D deployment, the Edge ML repository 806 can share its stored information to Central ML repository 806. The information may include ML repository ID and the registered information of AIMLE server / client 802.

[0107] Authorization Check (812) - The AIMLE server 804 validates the registration request and performs an authentication and authorization check to determine if the AIMLE server / client 802 is permitted to register to the AIMLE server 804 and participate in AI / ML operations.

[0108] Registration request 813 / Registration response 814 - Upon successful authorization, the AIMLE server 804 saves the context of the AIMLE client registration to the ML repository 806. The context is the information in the registration request 811 from the AIMLE server / client 802.

[0109] AIMLE Registration response 815 - The AIMLE server 804 returns an AIMLE registration response 815 to the AIMLE server / client 802 with the status of the request. Besides the parameter in table 8.7.3.3-1 of 3GPP TS 23.482, the response 815 may include:

[0110] [COM] ML repository ID: identifier of the ML repository 806 where the AIMLE server / client 802 is registered to.[DMR-D] Central ML repository ID: identifier of the central ML repository 806 to which the edge ML repository 806 shared its registered information.

[0111] AIMLE Server / Client Discovery

[0112] Fig. 9 illustrates the discovery of an AIMLE Server / Client according to embodiments of the techniques described herein.

[0113] The AIMLE Server / Client discovery procedure can be as follows when there are AIMLE services with a hierarchical AIMLE server deployment. In Fig. 9, entity 906 can be a Central AIMLE server or a Central ML Repository, depending on the specific hierarchical AIMLE server deployment scenario. In particular, in the scenario illustrated in Fig. 6 (DMR-nD: Distributed ML Repository without direct connections between ML repositories), entity 906 is a Central AIMLE Server, and the edge AIMLE server 904 sends an AIMLE client request to the central AIMLE server 906, and the central AIMLE server 906 communicates with the central ML repository. In the scenario illustrated in Fig. 7, the edge AIMLE server 904 communicates with an edge ML repository (not shown in Fig. 9), and then the edge ML repository communicates with the central ML repository 906.

[0114] AIMLE Discovery request (911) - A consumer 902 (e.g. VAL server, AIMLE server / client) sends an AIMLE discovery request to an edge AIMLE server 904 to discover a list of AIMLE servers / clients that are available to participate in AI / ML operations. Besides the parameters in Table 8.8.3.1-1 of 3GPP TS 23.482, for discovery of an AIMLE server, the discovery request may include:

[0115] [COM] DNN and DNAI(s) that identify the EDN or DN where to discover the AIMLE server. [COM] AIMLE server discovery criteria: discovery criteria for finding suitable AIMLE servers for AIML operations.

[0116] The AIMLE server discovery criteria may contain requested AIMLE server capability (e.g. compute capability, communication capability with AIMLE clients, etc.), requested AIML model types, requested AIML operations, etc.

[0117] [COM] Requested role in AIML task topology (e.g. to be connected in a hierarchical or distributed architecture)

[0118] [DMR-nD, DMR-D] EAS ID: identifier of the EAS which the AIMLE server deployed to be discovered Besides the parameters in Table 8.8.3.1-1 of 3GPP TS 23.482, for discovery of an AIMLE client, the discovery request may include:

[0119] [COM] DNN and DNAI(s) that identify the EDN or DN where to discover AIMLE client.

[0120] [COM] Besides the parameters given in Table 8.8.3.2-2 of TS 23.482 [2], the AIMLE client discovery criteria may include: EAS ID(s) (with AIMLE server deployed) or AIMLE server ID(s) which serving the AIMLE client.

[0121] [COM] Requested role in AIML task topology (e.g. to be connected in a hierarchical or distributedarchitecture)

[0122] Authorization Check 912 The edge AIMLE server 904 performs authentication, and authorization checks to determine if the requestor 902 is able to discover AIMLE servers / clients.

[0123] Fig. 9 illustrates two procedures / cases depending on whether the edge AIMLE server 904 is able to discover the required AIMLE servers / clients from an edge ML repository (which is not shown in Fig. 9).

[0124] Case 1 is where the edge AIMLE server 904 is able to discover the required AIMLE servers / clients from an edge ML repository:

[0125]

[0126] AIMLE - If the requestor 902 is authorized, the edge AIMLE server 904 performs discovery of AIMLE servers / clients from an / the edge ML repository fulfilling the provided AIMLE server / client discovery criteria, and responds to the consumer 902 with the required AIMLE server / client information.

[0127] Case 2 is where the edge AIMLE server 904 is not able to discover the required AIMLE servers / clients from an edge ML repository:

[0128] AIMLE di

[0129]

[0130] - If the edge AIMLE server 904 determines that it cannot discover the required AIMLE servers / clients from an edge ML repository, then discovery from central ML repository 906 is needed:

[0131] [DMR-nD] The edge AIMLE server 904 sends an AIMLE client request 914 to the central AIMLE server 906 to discover the list of AIMLE servers / clients.

[0132] [DMR-D] The edge AIMLE server 904 performs discovery of AIMLE servers / clients from the central ML repository 906 via the edge ML repository (not shown in Fig. 9).

[0133] Discovers AIMLE server / client

[0134]

[0135] - If the requestor (the edge AIMLE server 904) is authorized, the central AIMLE server / central ML repository 906 performs the discovery of AIMLE servers / clients fulfilling the provided AIMLE server / client discovery criteria.

[0136]

[0137] AIMLE - [DMR-nD] The central AIMLE server 906 sends an AIMLE discovery response 916 to the edge AIMLE server 904 with the required information of list of AIMLE servers / clients.

[0138] [DMR-D] The central ML repository 906 sends an AIMLE discovery response to the edge AIMLE server 904 via the edge ML repository (not shown in Fig. 9) with the required information of list of AIMLE servers / clients.

[0139] AIMLE di;

[0140]

[0141] - The edge AIMLE server 904 sends an AIMLE discovery response 917 to the consumer 902 with the required information of list of AIMLE servers / clients.

[0142] Fig. 10 depicts a method performed by a first node in accordance with particular embodiments. The first nodeis part of a communication network, and is for use in a hierarchical AIMLE service. The first node may be an AIMLE server or an AIMLE client. The first node may perform the method in response to executing suitably formulated computer readable code. The computer readable code may be embodied or stored on a computer readable medium, such as a memory chip, optical disc, or other storage medium. The computer readable medium may be part of a computer program product.

[0143] The method begins at step 1002 in which the first node sends a request to register the first node in a repository node. The request is sent to a second node in the communication network.

[0144] The first node may be an AIMLE server. In this case, the second node may also be an AIMLE server. In embodiments where the first node is an AIMLE server, the request sent in step 1002 can comprise any of: an identifier for a DN or EDN in which the first node is located or deployed; a DNN of the DN or EDN in which the first node is located or deployed; a DNAI of the DN or EDN in which the first node is located or deployed; profile information for the first node; one or more parameters in Table 8.7.3.2-1 of 3GPP TS 23.482 v19.0.0; a role supported by the first node in Al ML task topology; and an identifier of an EAS that is deploying the first node; and an identifier of the AIMLE. The profile information for the first node can comprise any of: information on capability of the first node to support Al ML operations for VAL services; information on capability of the first node to support AIMLE service; information on computation capability of the first node; information on communication capability of the first node; information on supported AIML model types; and information on supported AIML operations.

[0145] Alternatively, the first node can be an AIMLE client. In this case, the second node can be an AIMLE server. In embodiments where the first node is an AIMLE client, the request sent in step 1002 can comprise any of: an identifier for a DN or EDN in which the first node is located or deployed; a DNN of the DN or EDN in which the first node is located or deployed; a DNAI of the DN or EDN in which the first node is located or deployed; one or more parameters in Table 87.3.2-2 of 3GPP TS 23.482 v19.0.0; a role supported by the first node in AIML task topology; and an identifier of an EAS or AIMLE server that is serving the first node.

[0146] The method in Fig. 10 also includes optional step 1004 in which the first node receives a response to the request for registration from the second node.

[0147] The response received in step 1004 can comprise any of: an identifier of a first repository node with which the first node is registered; an identifier of a central repository node with which the first repository node shared information about the registration of the first node; and one or more parameters in Table 87.3.3-1 of 3GPP TS 23.482 v19.0.0.

[0148] Fig. 11 depicts another method performed by a first node in accordance with particular embodiments. The first node is part of a communication network, and is for use in a hierarchical AIMLE service. The first node may be an AIMLE server, an AIMLE client, an AIMLE service consumer, an Edge AIMLE server or an Edge AIMLE Repository. The first node may perform the method in response to executing suitably formulated computer readable code. The computer readable code may be embodied or stored on a computer readable medium, such as a memory chip, optical disc, or other storage medium. The computer readable medium may be part of a computer program product.

[0149] The method begins at step 1102 in which the first node sends a request to discover one or more clients and / orservers to participate in Al ML operations. The request is sent to a second node in the communication network. A request to discover one or more servers sent in step 1102 can comprise any of: an identifier for a DN or EDN in which the one or more servers are located or deployed; a DNN of the DN or EDN in which the one or more servers are located or deployed; a DNAI of the DN or EDN in which the one or more servers are located or deployed; server discovery criteria for discovering one or more suitable servers for the Al ML operations; one or more parameters in Table 8.8.3.1-1 of 3GPP TS 23.482 v19.0.0; a requested role supported by the one or more servers in AIML task topology; and an identifier of an EAS that is deploying the one or more servers to be discovered. Server discovery criteria for discovering one or more suitable servers for the Al ML operations can comprise any of: criteria for a capability of the one or more servers; criteria for a computation capability of the one or more servers; criteria for a communication capability of the one or more servers; information on requested AIML model types; and information on requested AIML operations.

[0150] A request to discover one or more clients sent in step 1102 can comprise any of: an identifier for a DN or EDN in which the one or more clients are located or deployed; a DNN of the DN or EDN in which the one or more clients are located or deployed; a DNAI of the DN or EDN in which the one or more clients are located or deployed; client discovery criteria for discovering one or more suitable clients for the AIML operations; an identifier of a server that is serving the one or more clients to be discovered; one or more parameters in Table 8.8.3.2-2 of 3GPP TS 23.482 v19.0.0; a requested role supported by the one or more servers in AIML task topology; and an identifier of an EAS that is deploying one or more servers that are serving the one or more clients to be discovered. Client discovery criteria can comprise an identifier of an EAS that is deploying a server for the one or more clients to be discovered; and / or an identifier of a server that is serving the one or more clients to be discovered.

[0151] The method in Fig. 11 also includes optional step 1104 in which the first node receives a response to the discovery request from the second node. The response to the discovery request comprises information on one or more clients and / or servers to participate in the AIML operations.

[0152] In the method of Fig. 11, the first node can be an AIMLE client, an AIMLE server or an AIMLE service consumer. The second node may be an AIMLE server, e.g. an Edge AIMLE server.

[0153] Alternatively, the first node in the method of Fig. 11 can be an Edge AIMLE server and the second node can be an Edge ML Repository or a Central AIMLE server. In another alternative, the first node is an Edge ML Repository and the second node is a Central ML Repository.

[0154] Fig. 12 depicts a method performed by a second node in accordance with particular embodiments. The second node is part of a communication network, and is for use in a hierarchical AIMLE service. The second node may be an AIMLE server. The second node may perform the method in response to executing suitably formulated computer readable code. The computer readable code may be embodied or stored on a computer readable medium, such as a memory chip, optical disc, or other storage medium. The computer readable medium may be part of a computer program product.

[0155] The method begins at step 1202 in which the second node receives a request to register a first node in arepository node. The request is received from a first node in the communication network.

[0156] The first node may be an AIMLE server. In this case, the second node may also be an AIMLE server. In embodiments where the first node is an AIMLE server, the request received in step 1202 can comprise any of: an identifier for a DN or EDN in which the first node is located or deployed; a DNN of the DN or EDN in which the first node is located or deployed; a DNAI of the DN or EDN in which the first node is located or deployed; profile information for the first node; one or more parameters in Table 8.7.3.2-1 of 3GPP TS 23.482 v19.0.0; a role supported by the first node in AIML task topology; and an identifier of an EAS that is deploying the first node; and an identifier of the AIMLE. The profile information for the first node can comprise any of: information on capability of the first node to support AIML operations for VAL services; information on capability of the first node to support AIMLE service; information on computation capability of the first node; information on communication capability of the first node; information on supported AIML model types; and information on supported AIML operations.

[0157] Alternatively, the first node can be an AIMLE client. In this case, the second node can be an AIMLE server. In embodiments where the first node is an AIMLE client, the request received in step 1202 can comprise any of: an identifier for a DN or EDN in which the first node is located or deployed; a DNN of the DN or EDN in which the first node is located or deployed; a DNAI of the DN or EDN in which the first node is located or deployed; one or more parameters in Table 87.3.2-2 of 3GPP TS 23.482 v19.0.0; a role supported by the first node in AIML task topology; and an identifier of an EAS or AIMLE server that is serving the first node.

[0158] The method in Fig. 12 also includes optional step 1204 in which the second node sends the request for registration to a repository node. Prior to step 1204, the method may further comprise the second node performing an authentication and / or authorization check to determine if the first node is permitted to register in a repository node. Step 1204 can be performed if the first node is authenticated or authorized.

[0159] The method in Fig. 12 also includes optional step 1206 in which the second node sends a response to the request for registration to the first node. The response sent in step 1206 can comprise any of: an identifier of a first repository node with which the first node is registered; an identifier of a central repository node with which the first repository node shared information about the registration of the first node; and one or more parameters in Table 87.3.3-1 of 3GPP TS 23.482 v19.0.0.

[0160] Fig. 13 depicts another method performed by a second node in accordance with particular embodiments. The second node is part of a communication network, and is for use in a hierarchical AIMLE service. The second node may be an AIMLE server, an Edge AIMLE server, an Edge ML Repository, a Central AIMLE Server or a Central ML Repository. The second node may perform the method in response to executing suitably formulated computer readable code. The computer readable code may be embodied or stored on a computer readable medium, such as a memory chip, optical disc, or other storage medium. The computer readable medium may be part of a computer program product.The method begins at step 1302 in which the second node receives a request to discover one or more clients and / or servers to participate in AIML operations. The request is received from a first node in the communication network.

[0161] A request to discover one or more servers received in step 1302 can comprise any of: an identifier for a DN or EDN in which the one or more servers are located or deployed; a DNN of the DN or EDN in which the one or more servers are located or deployed; a DNAI of the DN or EDN in which the one or more servers are located or deployed; server discovery criteria for discovering one or more suitable servers for the AIML operations; one or more parameters in Table 8.8.3.1-1 of 3GPP TS 23.482 v19.0.0; a requested role supported by the one or more servers in AIML task topology; and an identifier of an EAS that is deploying the one or more servers to be discovered. Server discovery criteria for discovering one or more suitable servers for the AIML operations can comprise any of: criteria for a capability of the one or more servers; criteria for a computation capability of the one or more servers; criteria for a communication capability of the one or more servers; information on requested AIML model types; and information on requested AIML operations.

[0162] A request to discover one or more clients received in step 1302 can comprise any of: an identifier for a DN or EDN in which the one or more clients are located or deployed; a DNN of the DN or EDN in which the one or more clients are located or deployed; a DNAI of the DN or EDN in which the one or more clients are located or deployed; client discovery criteria for discovering one or more suitable clients for the AIML operations; an identifier of a server that is serving the one or more clients to be discovered; one or more parameters in Table 8.8.3.2-2 of 3GPP TS 23.482 v19.0.0; a requested role supported by the one or more servers in AIML task topology; and an identifier of an EAS that is deploying one or more servers that are serving the one or more clients to be discovered. Client discovery criteria can comprise an identifier of an EAS that is deploying a server for the one or more clients to be discovered; and / or an identifier of a server that is serving the one or more clients to be discovered.

[0163] The method in Fig. 13 also includes optional step 1304 in which the second node sends a response to the discovery request to the first node. The response to the discovery request comprises information on one or more clients and / or servers to participate in the AIML operations.

[0164] In the method of Fig. 13, the first node can be an AIMLE client, an AIMLE server or an AIMLE service consumer. The second node may be an AIMLE server, e.g. an Edge AIMLE server.

[0165] Alternatively, the first node in the method of Fig. 13 can be an Edge AIMLE server and the second node can be an Edge ML Repository or a Central AIMLE server. In another alternative, the first node is an Edge ML Repository and the second node is a Central ML Repository.

[0166] Prior to step 1304, the method may further comprise the second node performing an authentication and / or authorization check to determine if the first node is permitted to discover servers and / or clients. Step 1304 can be performed if the first node is authenticated or authorized.

[0167] In some embodiments, the method can further comprise the second node sending, to an edge repository node, a request to discover one or more clients and / or servers to participate in AIML operations. The method may furthercomprise the second node receiving, from the edge repository node, information on one or more clients and / or servers to participate in the Al ML operations.

[0168] In some embodiments, if the information on one or more clients and / or servers to participate in the Al ML operations cannot be discovered from an edge repository node, then the second node can send a request to discover one or more clients and / or servers to participate in Al ML operations. This request can be sent to a central repository node via the edge repository node, or sent to a central AIMLE server.

[0169] Fig. 14 shows an example of a communication system 1400. In the example, the communication system 1400 includes a telecommunication network 1402 that includes an access network 1404, such as a radio access network (RAN), and a core network 1406, which includes one or more core network nodes 1408.

[0170] The access network 1404 includes one or more access network nodes or base stations of various types, such as access network nodes 1410a and 1410b (one or more of which are also referred to as RAN network nodes or RAN nodes 1410 herein), or any other similar 3rdGeneration Partnership Project (3GPP) access nodes or non-3GPP access points (AP). Some embodiments of the access network 1404 may include more than one access network technology. The network nodes 1410 of access network 1404 facilitate direct or indirect connection of wireless devices, also referred to as user equipments (UEs), such as by connecting UEs 1412A, 1412B, 1412C, and 1412D (one or more of which may be generally referred to as UEs 1412) to the core network 1406 over one or more wireless connections.

[0171] Moreover, as will be appreciated by those of skill in the art, a network node is not necessarily limited to an implementation in which a radio portion and a baseband portion are supplied and integrated by a single vendor. Thus, it will be understood that network nodes include disaggregated implementations or portions thereof. For example, in some embodiments, the telecommunication network 1402 includes one or more Open-RAN (ORAN) network nodes. An ORAN network node is a node in the telecommunication network 1402 that supports an ORAN specification (e.g., a specification published by the O-RAN Alliance, or any similar organization) and may operate alone or together with other nodes to implement one or more functionalities of any node in the telecommunication network 1402, including one or more access network nodes 1410 and / or core network nodes 1408.

[0172] Examples of an ORAN network node include an open radio unit (O-RU), an open distributed unit (O-DU), an open central unit (O-CU), including an O-CU control plane (O-CU-CP) or an O-CU user plane (O-CU-UP), a RAN intelligent controller (RIC) (near-real time or non-real time) hosting software or software plug-ins, such as a near-real time control application (e.g., xApp) or a non-real time control application (e.g., rApp), or any combination thereof (the adjective "open” designating support of an ORAN specification). An ORAN network node may support a specification by, for example, supporting an interface defined by the ORAN specification, such as an A1, F1, W1, E1, E2, X2, Xn interface, an open fronthaul user plane interface, or an open fronthaul management plane interface. Moreover, an ORAN access node may be a logical node in a physical node. Furthermore, an ORAN network node may be implemented in a virtualization environment (described further below) in which one or more network functions are virtualized. For example, the virtualization environment may include an O-Cloud computing platform orchestrated bya Service Management and Orchestration (SMO) Framework via an 0-2 interface defined by the O-RAN Alliance or comparable technologies.

[0173] The network nodes 1410 facilitate direct or indirect connection of wireless devices / UEs 1412, such as by connecting UEs 1412a, 1412b, 1412c, and 1412d (one or more of which may be generally referred to as UEs 1412) to the core network 1406 over one or more wireless connections. The access network nodes 1410 may be, for example, access points (APs) (e.g. radio access points), base stations (BSs) (e.g. radio base stations, Node Bs, evolved Node Bs (eNBs) and New Radio (NR) NodeBs (gNBs)).

[0174] Example wireless communications over a wireless connection include transmitting and / or receiving wireless signals using electromagnetic waves, radio waves, infrared waves, and / or other types of signals suitable for conveying information without the use of wires, cables, or other material conductors. Moreover, in different embodiments, the communication system 1400 may include any number of wired or wireless networks, network nodes, UEs, and / or any other components or systems that may facilitate or participate in the communication of data and / or signals whether via wired or wireless connections. The communication system 1400 may include and / or interface with any type of communication, telecommunication, data, cellular, radio network, and / or other similar type of system.

[0175] The wireless devices / UEs 1412 may be any of a wide variety of communication devices, including wireless devices arranged, configured, and / or operable to communicate wirelessly with the network nodes 1410 and other communication devices. Similarly, the access network nodes 1410 are arranged, capable, configured, and / or operable to communicate directly or indirectly with the UEs 1412 and / or with other network nodes or equipment in the telecommunication network 1402 to enable and / or provide network access, such as wireless network access, and / or to perform other functions, such as administration in the telecommunication network 1402. More specifically, UEs 1412 may send messages, data, and / or other signals to network nodes 1408, 1410 or other elements of the telecommunications network 1402 by transmitting such signals to the relevant device directly without the signals passing through any intervening devices or by transmitting such signals to the relevant device indirectly through an intervening device (or multiple intervening devices) that then transmit the signal to the relevant device. Similarly, network nodes 1408, 1410 may send messages, data, and other signals to UEs 1412, other network nodes 1408, 1410, and other devices in telecommunications network 1402 directly or indirectly. As one specific example, a core network node 1408 may transmit a particular message to a UE 1412 by transmitting the message to an access network node 1410 that will then transmit the message to the intended UE 1412. Similarly, a core network node 1408 may receive a particular message from a UE 1412 by receiving the message from an access network node 1410 that itself received the message from the UE 1412.

[0176] In the depicted example, the core network 1406 connects elements of the access network 1404 (e.g. one or more of the access network nodes 1410) to one or more host computing systems, such as host 1416. These connections may be direct or indirect via one or more intermediary networks or devices. In other examples, network nodes may be directly coupled to hosts. The core network 1406 includes one more core network nodes (e.g. core network node 1408) of various types that are structured with hardware and software components. Features of thesecomponents may be substantially similar to those described with respect to the wireless devices / UEs, access network nodes, and / or hosts, such that the descriptions thereof are generally applicable to the corresponding components of the core network node 1408. Example core network nodes include functions of one or more of a Mobile Switching Center (MSC), Mobility Management Entity (MME), Home Subscriber Server (HSS), Access and Mobility Management Function (AMF), Session Management Function (SMF), Authentication Server Function (AUSF), Subscription Identifier De-concealing function (SIDF), Unified Data Management (UDM), Security Edge Protection Proxy (SEPP), Network Exposure Function (NEF), and / or a User Plane Function (UPF).

[0177] The host 1416 may be under the ownership or control of a service provider other than an operator or provider of the access network 1404 and / or the telecommunication network 1402. The host 1416 may be operated by the service provider or on behalf of the service provider. The host 1416 may host a variety of applications to provide one or more service. Examples of such applications include live and pre-recorded audio / video content, data collection services such as retrieving and compiling data on various ambient conditions detected by a plurality of UEs, analytics functionality, social media, functions for controlling or otherwise interacting with remote devices, functions for an alarm and surveillance center, or any other such function performed by a server.

[0178] As a whole, the communication system 1400 of Fig. 14 enables connectivity between the wireless devices / UEs, network nodes, and hosts. In that sense, the communication system may be configured to operate according to predefined rules or procedures, such as specific standards that include, but are not limited to: Global System for Mobile Communications (GSM); Universal Mobile Telecommunications System (UMTS); Long Term Evolution (LTE), and / or other suitable 2ndGeneration (2G), 3rdGeneration (3G), 4thGeneration (4G), 5thGeneration (5G) standards, or any applicable future generation standard (e.g. 6thGeneration (6G)); wireless local area network (WLAN) standards, such as the Institute of Electrical and Electronics Engineers (IEEE) 802.11 standards (WiFi); and / or any other appropriate wireless communication standard, such as the Worldwide Interoperability for Microwave Access (WiMax), Bluetooth, Z-Wave, Near Field Communication (NFC), ZigBee, LiFi, and / or any low-power wide-area network (LPWAN) standards such as LoRa and Sigfox. Moreover, the communication system 1400 may be configured to support multiple different standards, protocols, or other rule sets, with individual components supporting all of the relevant rule sets or with different components or sub-systems within the communication system 1400 supporting different standards, protocols, or rule sets.

[0179] As one example, in certain embodiments, access network 1404 may contain some access network nodes 1410 that support 3GPP radio access technologies (RAT), such as LTE or NR, while other access network nodes 1410 support (or the same access network nodes 1410 additionally support) non-3GPP RATs, such as Wi-Fi or a proprietary RAT. As another example, telecommunications network 1402 may support multiple generations of related communication standards (e.g., 4G and 5G 3GPP communication standards) and, as a result, may include an access network 1404 and / or a core network 1406 that supports multiple different standard generations or may include multiple access networks 1404 and / or multiple core networks 1406 with individual networks 1404, 1406 supporting different standard generations.In some examples, the telecommunication network 1402 is a cellular network that implements 3GPP standardized features. Accordingly, the telecommunications network 1402 may support network slicing to provide different logical networks to different devices that are connected to the telecommunication network 1402. For example, the telecommunications network 1402 may provide Ultra Reliable Low Latency Communication (URLLC) services to some UEs, while providing Enhanced Mobile Broadband (eMBB) services to other UEs, and / or Massive Machine Type Communication (mMTC) / Massive IoT services to yet further UEs.

[0180] In some examples, the UEs 1412 are configured to transmit and / or receive information without direct human interaction. For instance, a UE may be designed to transmit information to the access network 1404 on a predetermined schedule, when triggered by an internal or external event, or in response to requests from the access network 1404. Additionally, a UE may be configured for operating in single- or multi-Radio Access Technology (RAT) or multi-standard mode. For example, a UE may operate with any one or combination of Wi-Fi, NR (New Radio) and LTE, i.e. being configured for multi-radio dual connectivity (MR-DC), such as E-UTRAN (Evolved-UTRA (UMTS Terrestrial Radio Access) Network) New Radio - Dual Connectivity (EN-DC).

[0181] In the example, the hub 1414 communicates with the access network 1404 to facilitate indirect communication between one or more UEs (e.g., UE 1412c and / or 1412d) and network nodes (e.g., network node 1410b). In some examples, the hub 1414 may be a controller, router, content source and analytics, or any of the other communication devices described herein regarding UEs. For example, the hub 1414 may be a broadband router enabling access to the core network 1406 for the UEs. As another example, the hub 1414 may be a controller that sends commands or instructions to one or more actuators in the UEs. Commands or instructions may be received from the UEs, network nodes 1410, or by executable code, script, process, or other instructions in the hub 1414. As another example, the hub 1414 may be a data collector that acts as temporary storage for UE data and, in some embodiments, may perform analysis or other processing of the data. As another example, the hub 1414 may be a content source. For example, for a UE that is a VR device, display, loudspeaker, or other media delivery device, the hub 1414 may retrieve VR assets, video, audio, or other media or data related to sensory information via a network node, which the hub 1414 then provides to the UE either directly, after performing local processing, and / or after adding additional local content. In still another example, the hub 1414 acts as a proxy server or orchestrator for the UEs, in particular if one or more of the UEs are low energy Internet of Things (loT) devices.

[0182] The hub 1414 may have a constant / persistent or intermittent connection to the network node 1410b. The hub 1414 may also allow for a different communication scheme and / or schedule between the hub 1414 and UEs (e.g., UE 1412c and / or 1412d), and between the hub 1414 and the core network 1406. In other examples, the hub 1414 is connected to the core network 1406 and / or one or more UEs via a wired connection. Moreover, the hub 1414 may be configured to connect to a machine-to-machine (M2M) service provider over the access network 1404 and / or to another UE over a direct connection. In some scenarios, UEs may establish a wireless connection with the network nodes 1410 while still connected via the hub 1414 via a wired or wireless connection. In some embodiments, the hub 1414 may be a dedicated hub - that is, a hub whose primary function is to route communications to / from the UEs from / tothe network node 1410b. In other embodiments, the hub 1414 may be a non-dedicated hub - that is, a device which is capable of operating to route communications between the UEs and network node 1410b, but which is additionally capable of operating as a communication start and / or end point for certain data channels.

[0183] Fig. 15 is a block diagram illustrating a virtualization environment 1500 in which functions implemented by some embodiments may be virtualized. In the present context, virtualizing means creating virtual versions of apparatuses or devices which may include virtualizing hardware platforms, storage devices and networking resources. As used herein, virtualization can be applied to any device described herein, or components thereof, and relates to an implementation in which at least a portion of the functionality is implemented as one or more virtual components. Some or all of the functions described herein may be implemented as virtual components executed by one or more virtual machines (VMs) implemented in one or more virtual environments 1500 hosted by one or more of hardware nodes, such as a hardware computing device that operates as an access network node, UE, core network node, host, AIMLE client, AIMLE server and / or ML repository. Further, in embodiments in which a virtual node does not require radio connectivity (e.g., a core network node, host, AIMLE client, AIMLE server, ML repository), then the node may be entirely virtualized. In some embodiments, the virtualization environment 1500 includes components defined by the O-RAN Alliance, such as an O-Cloud environment orchestrated by a Service Management and Orchestration Framework via an O-2 interface.

[0184] Applications 1502 (which may alternatively be called software instances, virtual appliances, network functions, virtual nodes, virtual network functions, etc.) are run in the virtualization environment 1500 to implement some of the features, functions, and / or benefits of some of the embodiments disclosed herein.

[0185] Hardware 1504 includes processing circuitry, memory that stores software and / or instructions executable by hardware processing circuitry, and / or other hardware devices as described herein, such as a network interface, input / output interface, and so forth. Software may be executed by the processing circuitry to instantiate one or more virtualization layers 1506 (also referred to as hypervisors or virtual machine monitors (VMMs)), provide VM 1508A and VM 1508B (which may be collectively referred to as VMs 1508), and / or perform any of the functions, features and / or benefits described in relation with some embodiments described herein. The virtualization layer 1506 may present a virtual operating platform that appears like networking hardware to one or more of the VMs 1508.

[0186] The VMs 1508 comprise virtual processing, virtual memory, virtual networking or interface and virtual storage, and may be run by virtualization layer 1506. Different embodiments of the instance of a virtual appliance 1502 may be implemented on one or more of VMs 1508, and the implementations may be made in different ways. Virtualization of the hardware is in some contexts referred to as network function virtualization (NFV). NFV may be used to consolidate many network equipment types onto industry standard high volume server hardware, physical switches, and physical storage, which can be located in data centers, and customer premise equipment.

[0187] In the context of NFV, each of the VMs 1508 may be a software implementation of a physical machine that runs programs as if they were executing on a physical, non-virtualized machine. Each of the VMs 1508, and that part of hardware 1504 that executes that VM, be it hardware dedicated to that VM and / or hardware shared by that VM with others of the VMs, forms separate virtual network elements. Still in the context of NFV, a virtual network function isresponsible for handling specific network functions that run in one or more of the VMs 1508 on top of the hardware 1504 and corresponds to an application 1502.

[0188] Hardware 1504 may be implemented in a standalone network node with generic or specific components. Hardware 1504 may implement some functions via virtualization. Alternatively, hardware 1504 may be part of a larger cluster of hardware (e.g. such as in a data center or CPE) where many hardware nodes work together and are managed via management and orchestration 1510, which, among others, oversees lifecycle management of applications 1502. In some embodiments, hardware 1504 is coupled to one or more radio units that each include one or more transmitters and one or more receivers that may be coupled to one or more antennas. Radio units may communicate directly with other hardware nodes via one or more appropriate network interfaces and may be used in combination with the virtual components to provide a virtual node with radio capabilities, such as a radio access node or a base station. In some embodiments, some signalling can be provided with the use of a control system 1512 which may alternatively be used for communication between hardware nodes and radio units.

[0189] Although the computing devices described herein (e.g., UEs, network nodes, hosts) may include the illustrated combination of hardware components, other embodiments may comprise computing devices with different combinations of components. It is to be understood that these computing devices may comprise any suitable combination of hardware and / or software needed to perform the tasks, features, functions and methods disclosed herein. Determining, calculating, obtaining or similar operations described herein may be performed by processing circuitry, which may process information by, for example, converting the obtained information into other information, comparing the obtained information or converted information to information stored in the network node, and / or performing one or more operations based on the obtained information or converted information, and as a result of said processing making a determination. Moreover, while components are depicted as single boxes located within a larger box, or nested within multiple boxes, in practice, computing devices may comprise multiple different physical components that make up a single illustrated component, and functionality may be partitioned between separate components. For example, a communication interface may be configured to include any of the components described herein, and / or the functionality of the components may be partitioned between the processing circuitry and the communication interface. In another example, non-computationally intensive functions of any of such components may be implemented in software or firmware and computationally intensive functions may be implemented in hardware.

[0190] In certain embodiments, some or all of the functionality described herein may be provided by processing circuitry executing instructions stored on in memory, which in certain embodiments may be a computer program product in the form of a non-transitory computer-readable storage medium. In alternative embodiments, some or all of the functionality may be provided by the processing circuitry without executing instructions stored on a separate or discrete device-readable storage medium, such as in a hard-wired manner. In any of those particular embodiments, whether executing instructions stored on a non-transitory computer-readable storage medium or not, the processing circuitry can be configured to perform the described functionality. The benefits provided by such functionality are not limited tothe processing circuitry alone or to other components of the computing device, but are enjoyed by the computing device as a whole, and / or by end users and a wireless network generally.

[0191] Fig. 16 shows a core network node 1600 in accordance with some embodiments. As used herein, core network node refers to equipment capable, configured, arranged and / or operable to communicate directly or indirectly with a UE and / or with other core network nodes or equipment or RAN network nodes, in a telecommunication network. The core network node 1600 may be operable as a core network node, a core network function or, more generally, a core network entity, such as the core network node 1408 described above with respect to Fig. 14. Examples of core network nodes in this context include core network entities such as one or more of a AIMLE client, Al MLE server, ML Repository, Mobile Switching Center (MSC), Mobility Management Entity (MME), Home Subscriber Server (HSS), Access and Mobility Management Function (AMF), Session Management Function (SMF), Authentication Server Function (AUSF), Subscription Identifier De-concealing function (SIDF), Unified Data Management (UDM), Security Edge Protection Proxy (SEPP), Network Exposure Function (NEF), and / or a User Plane Function (UPF).

[0192] The core network node 1600 includes processing circuitry 1602, a memory 1604, a communication interface 1606, and a power source 1608, and / or any other component, or any combination thereof. The core network node 1600 may be composed of multiple physically separate components, which may each have their own respective components. In certain scenarios in which the core network node 1600 comprises multiple separate components, one or more of the separate components may be shared among several core network nodes.

[0193] The processing circuitry 1602 may comprise a combination of one or more of a microprocessor, controller, microcontroller, central processing unit, digital signal processor, application-specific integrated circuit, field programmable gate array, or any other suitable computing device, resource, or combination of hardware, software and / or encoded logic operable to provide, either alone or in conjunction with other core network node 1600 components, such as the memory 1604, core network node 1600 functionality. For example, the processing circuitry 1602 may be configured to cause the network node to perform the methods as described herein.

[0194] The memory 1604 may comprise any form of volatile or non-volatile computer-readable memory including, without limitation, persistent storage, solid-state memory, remotely mounted memory, magnetic media, optical media, random access memory (RAM), read-only memory (ROM), mass storage media (for example, a hard disk), removable storage media (for example, a flash drive, a Compact Disk (CD) or a Digital Video Disk (DVD)), and / or any other volatile or non-volatile, non-transitory device-readable and / or computer-executable memory devices that store information, data, and / or instructions that may be used by the processing circuitry 1602. The memory 1604 may store any suitable instructions, data, or information, including a computer program, software, an application including one or more of logic, rules, code, tables, and / or other instructions capable of being executed by the processing circuitry 1602 and utilized by the core network node 1600. The memory 1604 may be used to store any calculations made by the processing circuitry 1602 and / or any data received via the communication interface 1606. In some embodiments, the processing circuitry 1602 and memory 1604 are integrated.

[0195] The communication interface 1606 is used in wired or wireless communication of signalling and / or data betweena core network node, access network node(s), and / or UE.

[0196] The power source 1608 provides power to the various components of core network node 1600 in a form suitable for the respective components (e.g., at a voltage and current level needed for each respective component). The power source 1608 may further comprise, or be coupled to, power management circuitry to supply the components of the core network node 1600 with power for performing the functionality described herein. For example, the core network node 1600 may be connectable to an external power source (e.g., the power grid, an electricity outlet) via an input circuitry or interface such as an electrical cable, whereby the external power source supplies power to power circuitry of the power source 1608. As a further example, the power source 1608 may comprise a source of power in the form of a battery or battery pack which is connected to, or integrated in, power circuitry. The battery may provide backup power should the external power source fail.

[0197] Embodiments of the core network node 1600 may include additional components beyond those shown in Fig.

[0198] 16 for providing certain aspects of the core network node's functionality, including any of the functionality described herein and / or any functionality necessary to support the subject matter described herein. For example, the core network node 1600 may include user interface equipment to allow input of information into the core network node 1600 and to allow output of information from the core network node 1600. This may allow a user to perform diagnostic, maintenance, repair, and other administrative functions for the core network node 1600.

[0199] Although the computing devices described herein (e.g., wireless devices, UEs, network nodes) may include the illustrated combination of hardware components, other embodiments may comprise computing devices with different combinations of components. It is to be understood that these computing devices may comprise any suitable combination of hardware and / or software needed to perform the tasks, features, functions and methods disclosed herein. Determining, calculating, obtaining or similar operations described herein may be performed by processing circuitry, which may process information by, for example, converting the obtained information into other information, comparing the obtained information or converted information to information stored in the network node, and / or performing one or more operations based on the obtained information or converted information, and as a result of said processing making a determination. Moreover, while components are depicted as single boxes located within a larger box, or nested within multiple boxes, in practice, computing devices may comprise multiple different physical components that make up a single illustrated component, and functionality may be partitioned between separate components. For example, a communication interface may be configured to include any of the components described herein, and / or the functionality of the components may be partitioned between the processing circuitry and the communication interface. In another example, non-computationally intensive functions of any of such components may be implemented in software or firmware and computationally intensive functions may be implemented in hardware.

[0200] In certain embodiments, some or all of the functionality described herein may be provided by processing circuitry executing instructions stored on in memory, which in certain embodiments may be a computer program product in the form of a non-transitory computer-readable storage medium. In alternative embodiments, some or all of the functionality may be provided by the processing circuitry without executing instructions stored on a separate or discretedevice-readable storage medium, such as in a hard-wired manner. In any of those particular embodiments, whether executing instructions stored on a non-transitory computer-readable storage medium or not, the processing circuitry can be configured to perform the described functionality. The benefits provided by such functionality are not limited to the processing circuitry alone or to other components of the computing device, but are enjoyed by the computing device as a whole, and / or by end users and a wireless network generally.

[0201] The foregoing merely illustrates the principles of the disclosure. Various modifications and alterations to the described embodiments will be apparent to those skilled in the art in view of the teachings herein. It will thus be appreciated that those skilled in the art will be able to devise numerous systems, arrangements, and procedures that, although not explicitly shown or described herein, embody the principles of the disclosure and can be thus within the scope of the disclosure. Various exemplary embodiments can be used together with one another, as well as interchangeably therewith, as should be understood by those having ordinary skill in the art.APPENDIX

[0202] 3GPP TSG-SA WG6 Meeting #66 S6-25xxxx Goteborg, Sweden, 7th - 11th April 2025

[0203] Title: New Key Issue on Hierarchical and Distributed AIMLE Services

[0204] Spec: 3GPP TR 23. XYZ vO. O. O

[0205] Agenda item:

[0206]

[0207] Document for: Approval

[0208] 1. Introduction

[0209] This pCR proposes new Key Issue for FS_AIMLAPP_Ph2.

[0210] 2. Reason for Change

[0211] The New SID for study on application enablement for AI / ML service; Phase 2 (S6-250559) was approved in S \ I ( r meeting. According to the approved SID, the objective of the study is to enhance the support for AI / ML services at application enablement layer, which include

[0212] 1. Study AIMLE enhancements to support the following aspects:

[0213] a. Enhancements related to ML model performance monitoring and correctness evaluation.

[0214] b. Extensions to split AIML operations enablement e.g., split AIML operation involving multiple VAL UEs.

[0215] c. Enhancements in VFL support considering also VFL participants at the server side, e.g., sample alignment across VAL / AIMLE severs.

[0216] d. Study potential enhancements to AIMLE services operating in multi-MNO scenarios and assuring service continuity support across MNOs and CSPs / ECSPs, with support for roaming and federation scenarios.

[0217] e. Identify the impacts and study potential enhancements for supporting AIMLE services assuming diverse (e.g., hierarchical and distributed) AIMLE deployments.

[0218] 2. Study architecture implications when using AI / ML model inference in AD AES for ML-enabled analytics, considering also hierarchical or distributed AD AES deployments and distributed ADAE analytics e.g. in both ADAEC and AD AES.

[0219] 3. Study potential enhancements in AIMLE based on AI / ML related capabilities provided by SA2 (for core network support) and SA5 (for ML model lifecycle management aspects).

[0220] 4. Identify potential solutions as required, including the information flows and the APIs satisfying the architectural requirements and enhancements identified in bullets 1), 2) and 3).

[0221] Therefore, a new Key Issue is proposed for the study of the objective le) on diverse AIMLE services, including hierarchical and distributed AIMLE services.

[0222] 3. Conclusions

[0223] This paper proposes a new Key Issue is proposed for the study of the objective le) on diverse AIMLE services, including hierarchical and distributed AIMLE services.

[0224] 4. Proposal

[0225] It is proposed to agree the following changes to 3GPP TR 23. XYZ.

[0226]

[0227] * * * First Change * * * *

[0228] Xc. Yc Key Issue #C: Hierarchical and Distributed AIMLE Services

[0229] SA6 Rel-19 AIML ADD (in 3GPP TS 23,482) studied support of AIML services for assisting hierarchical computing, which allows the consumer (e.g. CAS. EAS) to request AIMLE server for hierarchical computing assistance information to support its operations.

[0230] In addition, different deployment models are introduced, for example:

[0231] ■ Cloud-deployed AIMLE server

[0232] ■ Edge-deployed AIMLE server

[0233] ■ Hierarchical AIMLE server deployment

[0234] In Rel-20, supporting AIMLE capabilities in scenarios where the AIMLE is deployed in distributed or hierarchical fashion requires more investigation. In this study, it is expected to explore potential enhancement for supporting such deployments, considering also different implementations of the ML repository in edge or cloud platforms, and different assumptions on the access of ML repositories by VAL and other enablers. In this regard, considering the various AIML capabilities provided by the VAL UE, the collaboration procedures among AIMLE Clients, edge AIMLE servers, and central AIMLE servers need to be enhanced in terms of data management and AIML operation splitting.

[0235] The new SID study on application enablement for AI / ML service; Phase 2, list the objective of the study include:

[0236] ■ Identify the impacts and study potential enhancements for supporting AIMLE services assuming diverse (e.g.. hierarchical and distributed) AIMLE deployments.

[0237] Therefore, to support enhancements related to hierarchical and distributed AIMLE services, the following aspects need to be studied:

[0238] - How and which AIMLE capability can be deployed hierarchically?

[0239] - What AIML operations can take benefit of the hierarchical AIMLE deployments?

[0240] - How to support AIML service continuity in the hierarchical architecture?

[0241] - What AIMLE capability and AIML operation can be considered under distributed architecture?

[0242] - Whether and what enhancements to existing mechanisms are needed to support hierarchical and distributed AIMLE services?

[0243]

[0244] * * * End of Changes * * * *

Claims

1. CLAIMS1. A method performed by a first node in a communication network, wherein the first node is for use in a hierarchical Artificial Intelligence Machine Learning, AIML, Enablement, AIMLE, service, the method comprising:sending (1002), to a second node in the communication network, a request to register the first node in a repository node.

2. The method of claim 1, wherein first node is an AIMLE server, and the request to register the first node comprises any of:an identifier for a data network, DN, or edge DN, EDN, in which the first node is located or deployed;a Data Network Name, DNN, of the DN or EDN in which the first node is located or deployed;a Data Network Access Identifier, DNAI, of the DN or EDN in which the first node is located or deployed; profile information for the first node;profile information for the first node that comprises any of:information on capability of the first node to support AIML operations for Vertical Application Layer, VAL, services;information on capability of the first node to support AIMLE service;information on computation capability of the first node;information on communication capability of the first node;information on supported AIML model types; andinformation on supported AIML operations;a role supported by the first node in AIML task topology;an identifier of an Edge Application Server, EAS, that is deploying the first node; andan identifier of the AIMLE.

3. The method of claim 1, wherein first node is an AIMLE client, and the request to register the first node comprises any of:an identifier for a data network, DN, or edge DN, EDN, in which the first node is located or deployed;a Data Network Name, DNN, of the DN or EDN in which the first node is located or deployed;a Data Network Access Identifier, DNAI, of the DN or EDN in which the first node is located or deployed; a role supported by the first node in AIML task topology;an identifier of an Edge Application Server, EAS, or AIMLE server that is serving the first node.

4. The method of any of claims 1-3, wherein the method further comprises:receiving (1004), from the second node, a response to the request for registration.

5. The method of claim 4, wherein the response to the request for registration comprises any of: an identifier of a first repository node with which the first node is registered; andan identifier of a central repository node with which the first repository node shared information about the registration of the first node.

6. The method of any of claims 1-5, wherein:the first node is a AIMLE client and the second node is an AIMLE server; orthe first node is an AIMLE server, and the second node is an AIMLE server.

7. A method performed by a first node in a communication network, wherein the first node is for use in a hierarchical Artificial Intelligence Machine Learning, AIML, Enablement, AIMLE, service, the method comprising:sending (1102), to a second node in the communication network, a request to discover one or more clients and / or servers to participate in AIML operations.

8. The method of claim 7, wherein a request to discover one or more servers comprises any of:an identifier for a data network, DN, or edge DN, EDN, in which the one or more servers are located or deployed; a Data Network Name, DNN, of the DN or EDN in which the one or more servers are located or deployed; a Data Network Access Identifier, DNAI, of the DN or EDN in which the one or more servers are located or deployed;discovery criteria for discovering one or more suitable servers for the AIML operations;server discovery criteria for discovering one or more suitable servers for the AIML operations that comprises any of:criteria for a capability of the one or more servers;criteria for a computation capability of the one or more servers;criteria for a communication capability of the one or more servers;information on requested AIML model types; andinformation on requested AIML operations;a requested role supported by the one or more servers in AIML task topology;an identifier of an Edge Application Server, EAS, that is deploying the one or more servers to be discovered.

9. The method of claim 7, wherein a request to discover one or more clients comprises any of:an identifier for a data network, DN, or edge DN, EDN, in which the one or more clients are located or deployed; a Data Network Name, DNN, of the DN or EDN in which the one or more clients are located or deployed;a Data Network Access Identifier, DNAI, of the DN or EDN in which the one or more clients are located or deployed;discovery criteria for discovering one or more suitable clients for the Al ML operations;client discovery criteria for discovering one or more suitable clients for the Al ML operations that comprises any of:an identifier of an Edge Application Server, EAS, that is deploying a server for the one or more clients to be discovered; andan identifier of a server that is serving the one or more clients to be discovered;a requested role supported by the one or more servers in AIML task topology;an identifier of an Edge Application Server, EAS, that is deploying one or more servers that are serving the one or more clients to be discovered.

10. The method of claim 7, 8 or 9, wherein the method further comprises:receiving (1104), from the second node, a response to the discovery request that comprises information on one or more clients and / or servers to participate in the AIML operations.

11. The method of any of claims 7-10, wherein the first node is a AIMLE client, an AIMLE server or an AIMLE service consumer, and the second node is an AIMLE server.

12. The method of claim 11, wherein the second node is an Edge AIMLE server.

13. The method of any of claims 7-10, wherein one of:the first node is an Edge AIMLE server and the second node is an Edge ML Repository or a Central AIMLE server; andthe first node is an Edge ML Repository and the second node is a Central ML Repository.

14. A method performed by a second node in a communication network, wherein the second node is for use in a hierarchical Artificial Intelligence, Al, Machine Learning, ML, Enablement, AIMLE, service, the method comprising:receiving (1202), from a first node in the communication network, a request to register the first node in a repository node.

15. The method of claim 14, wherein first node is an AIMLE server, and the request to register the first node comprises any of:an identifier for a data network, DN, or edge DN, EDN, in which the first node is located or deployed;a Data Network Name, DNN, of the DN or EDN in which the first node is located or deployed;a Data Network Access Identifier, DNAI, of the DN or EDN in which the first node is located or deployed; profile information for the first node;profile information for the first node that comprises any of:information on capability of the first node to support AIML operations for Vertical Application Layer, VAL, services;information on capability of the first node to support AIMLE service;information on computation capability of the first node;information on communication capability of the first node;information on supported AIML model types; andinformation on supported AIML operations;a role supported by the first node in AIML task topology;an identifier of an Edge Application Server, EAS, that is deploying the first node; andan identifier of the AIMLE.

16. The method of claim 14, wherein first node is an AIMLE client, and the request to register the first node comprises any of:an identifier for a data network, DN, or edge DN, EDN, in which the first node is located or deployed;a Data Network Name, DNN, of the DN or EDN in which the first node is located or deployed;a Data Network Access Identifier, DNAI, of the DN or EDN in which the first node is located or deployed; a role supported by the first node in AIML task topology;an identifier of an Edge Application Server, EAS, or AIMLE server that is serving the first node.

17. The method of any of claims 14-16, wherein the method further comprises:sending (1206), to the first node, a response to the request for registration.

18. The method of claim 17, wherein the response to the request for registration comprises any of:an identifier of a first repository node with which the first node is registered; andan identifier of a central repository node with which the first repository node shared information about the registration of the first node.

19. The method of any of claims 14-18, wherein:the first node is a AIMLE client and the second node is an AIMLE server; orthe first node is an AIMLE server, and the second node is an AIMLE server.

20. The method of any of claims 14-19, wherein the method further comprises:performing an authentication and / or authorization check to determine if the first node is permitted to register in a repository node.

21. The method of any of claims 14-20, wherein the method further comprises:sending (1204), to a repository node, a request to register the first node.

22. A method performed by a second node in a communication network, wherein the second node is for use in a hierarchical Artificial Intelligence Machine Learning, AIML, Enablement, AIMLE, service, the method comprising: receiving (1302), from a first node in the communication network, a request to discover one or more clients and / or servers to participate in AIML operations.

23. The method of claim 22, wherein a request to discover one or more servers comprises any of:an identifier for a data network, DN, or edge DN, EDN, in which the one or more servers are located or deployed; a Data Network Name, DNN, of the DN or EDN in which the one or more servers are located or deployed; a Data Network Access Identifier, DNAI, of the DN or EDN in which the one or more servers are located or deployed;discovery criteria for discovering one or more suitable servers for the AIML operations;server discovery criteria for discovering one or more suitable servers for the AIML operations that comprises any of:criteria for a capability of the one or more servers;criteria for a computation capability of the one or more servers;criteria for a communication capability of the one or more servers;information on requested AIML model types; andinformation on requested AIML operations;a requested role supported by the one or more servers in AIML task topology;an identifier of an Edge Application Server, EAS, that is deploying the one or more servers to be discovered.

24. The method of claim 22, wherein a request to discover one or more clients comprises any of:an identifier for a data network, DN, or edge DN, EDN, in which the one or more clients are located or deployed; a Data Network Name, DNN, of the DN or EDN in which the one or more clients are located or deployed; a Data Network Access Identifier, DNAI, of the DN or EDN in which the one or more clients are located or deployed;discovery criteria for discovering one or more suitable clients for the AIML operations;client discovery criteria for discovering one or more suitable clients for the AIML operations that comprises any of:an identifier of an Edge Application Server, EAS, that is deploying a server for the one or more clients to be discovered; andan identifier of a server that is serving the one or more clients to be discovered;a requested role supported by the one or more clients in Al ML task topology;an identifier of an Edge Application Server, EAS, that is deploying one or more servers that are serving the one or more clients to be discovered.

25. The method of any of claims 22-24, wherein the method further comprises:sending (1304), to the first node, a response to the discovery request that comprises information on one or more clients and / or servers to participate in the AIML operations.

26. The method of any of claims 22-25, wherein the first node is a AIMLE client, an AIMLE server or an AIMLE service consumer, and the second node is an AIMLE server.

27. The method of claim 26, wherein the second node is an Edge AIMLE server.

28. The method of any of claims 22-27, wherein the method further comprises:performing an authentication and / or authorization check to determine if the first node is permitted to discover servers and / or clients.

29. The method of any of claims 22-28, wherein the method further comprises:sending, to an edge repository node, a request to discover one or more clients and / or servers to participate in AIML operations.

30. The method of claim 29, wherein the method further comprises:receiving, from the edge repository node, information on one or more clients and / or servers to participate in the AIML operations.

31. The method of any of claims 22-30, wherein if the information on one or more clients and / or servers to participate in the AIML operations cannot be discovered from an edge repository node, the method further comprises:sending a request to discover one or more clients and / or servers to participate in AIML operations, wherein the request is sent to a central repository node via the edge repository node, or sent to a central AIMLE server.

32. The method of any of claims 22-25, wherein one of:the first node is an Edge AIMLE server and the second node is an Edge ML Repository or a Central AIMLE server; andthe first node is an Edge ML Repository and the second node is a Central ML Repository.

33. A method performed by a node in a communication network, wherein the method comprises two or more of:performing the method according to any of claims 1-6;performing the method according to any of claims 7-13;performing the method according to any of claims 14-21; andperforming the method according to any of claims 22-32.

34. A computer program product comprising a computer readable medium having computer readable code embodied therein, the computer readable code being configured such that, on execution by a suitable computer or processor, the computer or processor is caused to perform the method of any of claims 1-33.

35. A node configured to perform the method of any of claims 1-33.

36. A node comprising a processor and a memory, said memory containing instructions executable by said processor whereby said node is operative to perform the method of any of claims 1-33.

Images