EP-4742118-A2 - METHODS, APPARATUS AND MACHINE-READALE MEDIA RELATING TO MACHINE-LEARNING IN A COMMUNICATION NETWORK

Abstract

In one aspect, a method performed by a network entity in a communications network is provided. The method comprises obtaining identification information for a plurality of candidate network entities in the communications network, in which the identification information indicates that each of the candidate network entities is configured to participate in collaborative learning. The method further comprises sending a request for each of the candidate network entities, in which the request comprises one or more selection criteria, and receiving one or more response messages comprising an indication of which of the candidate network entities satisfy the one or more selection criteria. Based on the indication in the one or more response messages, the network entity selects one or more of the plurality of candidate network entities to participate in a collaborative learning process to train a model using a machine learning algorithm.

Inventors

• NORRMAN, KARL
• ISAKSSON, MARTIN

Assignees

• Telefonaktiebolaget LM Ericsson (publ)

Dates

Publication Date

20260513

Application Date

20200806

Claims (17)

1. A method performed by a network entity or a distributed system of network entities (800; 900) in a communications network, the method comprising: obtaining (502) identification information for a plurality of candidate network entities in the communications network, the identification information indicating that the candidate network entities are configured to participate in collaborative learning; sending (504) a request towards each of the plurality of candidate network entities, the request comprising one or more selection criteria; receiving (506) one or more response messages comprising an indication of which of the candidate network entities satisfy the one or more selection criteria; and based on the indication in the one or more response messages, selecting (508) one or more of the plurality of candidate network entities to participate in a collaborative learning process to train a model using a machine learning algorithm.
2. A method performed by a first network entity or a distributed system of first network entities (1000; 1100) in a communications network, the first network entity belonging to a plurality of network entities configured to participate in collaborative learning, the method comprising: receiving (602) a request from a second network entity in the communications network, the request comprising one or more selection criteria for selecting network entities to participate in a collaborative learning process to train a model using a machine learning algorithm; and transmitting (604), to the second network entity in the communications network, a response message comprising an indication of whether the first network entity satisfies the one or more selection criteria.
3. A network entity or a distributed system of network entities for a communications network, the network entity or distributed system (800) comprising processing circuitry (802) and a non-transitory machine-readable medium (804) storing instructions which, when executed by the processing circuitry, cause the network entity to: obtain (502) identification information for a plurality of candidate network entities in the communications network, the identification information indicating that the candidate network entities are configured to participate in collaborative learning; send (504) a request towards each of the plurality of candidate network entities, the request comprising one or more selection criteria; receive (506) one or more response messages comprising an indication of which of the candidate network entities satisfy the one or more selection criteria; and based on the indication in the one or more response messages, select (508) one or more of the plurality of candidate network entities to participate in a collaborative learning process to train a model using a machine learning algorithm.
4. The network entity of claim 3, wherein the one or more selection criteria comprise one or more of the following: a criterion relating to a configuration of the candidate network entity; a criterion relating to performance requirements for the candidate network entity; a criterion relating to availability of training data at the candidate network entity for training the model; and a criterion relating to a property of training data available at the candidate network entity.
5. The network entity of any of claims 3-4, wherein the one or more selection criteria comprise a criterion relating to one or more metrics indicative of a performance of a preliminary model obtained by training the model at the candidate network entity using the machine learning algorithm.
6. The network entity of claim 5, wherein sending a request towards each of the plurality of candidate network entities comprises initiating, at the candidate network entities, training of the model to obtain the preliminary model.
7. The network entity of any of claims 3-6, wherein sending a request towards each of the plurality of candidate network entities comprises sending a request for the candidate network entities to an operations, administration and maintenance, OAM, entity in the communications network.
8. The network entity of claim 7, wherein the request further comprises a maximum number of candidate network entities to be selected by the OAM for participating in the collaborative learning process, and the one or more response messages comprise an indication for only a subset of the plurality of candidate network entities.
9. The network entity of any of claims 3-8, wherein the network entity is further caused to: receive, for at least one candidate network entity in the plurality of candidate network entities, one or more participation criteria for participating in the collaborative learning process, wherein selection of the one or more of the plurality of candidate network entities to participate in the collaborative learning process is further based on whether or not the one or more participation criteria are satisfied.
10. A first network entity or a distributed system of first network entities (1000) for a communications network, the first network entity or distributed system belonging to a plurality of network entities configured to participate in collaborative learning, the first network entity comprising processing circuitry (1002) and a non-transitory machine-readable medium (1004) storing instructions which, when executed by the processing circuitry, cause the first network entity to: receive (602) a request from a second network entity in the communications network, the request comprising one or more selection criteria for selecting network entities to participate in a collaborative learning process to train a model using a machine learning algorithm; and transmit (604), to the second network entity in the communications network, a response message comprising an indication of whether the first network entity satisfies the one or more selection criteria.
11. The first network entity of claim 10, wherein the one or more selection criteria comprise one or more of the following: a criterion relating to a configuration of the first network entity; a criterion relating to an availability of training data, at the first network entity, for training the model; and a criterion relating to a property of training data available at the first network entity.
12. The first network entity of any of claims 10-11, wherein the one or more selection criteria comprise a criterion relating to one or more metrics indicative of a performance of a preliminary model obtained at the first network entity by training the model using the machine learning algorithm.
13. The first network entity of claim 12, wherein the first network entity is further caused to: obtain values of the one or more metrics for the preliminary model; and compare the obtained values to the at least one of the one or more selection criteria.
14. The first network entity of any of claims 10-13, wherein the response message further comprises one or more participation criteria for participating in the collaborative learning process.
15. The first network entity of claim 14, wherein the one or more participation criteria relate to one or more of the following: a network slice operated on by the second network entity; and a threshold number of other network entities participating in the collaborative learning process.
16. The first network entity of any of claims 11-15, wherein at least one of the following apply: the second network entity is a network data analytics function, NWDAF (308), or an operations, administration and maintenance, OAM, entity (312); and at least one of the first network entity and the second network entity are in a core network of a communications network.
17. A system in a communications network, the system comprising a first network entity (800; 900), and a plurality of second network entities (1000; 1100) configured to participate in collaborative learning, wherein the first network entity is configured to: obtain (502) identification for the plurality of second network entities, the identification information indicating that the second network entities are configured to participate in collaborative learning; and send (504) a request towards each of the plurality of second network entities, the request comprising one or more selection criteria, wherein the second network entities are further configured to receive (602) the request and one or more of the second network entities are configured to: transmit (604) a response message comprising an indication of whether the respective second network entity satisfies the one or more selection criteria, and wherein the first network entity is further configured to: receive (506) the one or more response messages; and based on the indication in the one or more response messages, select (508) one or more of the plurality of second network entities to participate in a collaborative learning process to train a model using a machine learning algorithm.

Description

Technical Field Embodiments of the disclosure relate to machine-learning, and particularly to methods, apparatus and machine-readable media relating to machine-learning in a communication network. Background In a typical wireless communication network, wireless devices are connected to a core network via a radio access network. In a fifth generation (5G) wireless communication network, the core network operates according to a Service Based Architecture (SBA), in which services are provided by network functions via defined application interfaces (APIs). Network functions in the core network use a common protocol framework based on Hypertext Transfer Protocol 2 (HTTP/2). As well as providing services, a network function can also invoke services in other network functions through these APIs. Examples of core network functions in the 5G architecture include the Access and mobility Management Function (AMF), Authentication Server Function (AUSF), Session Management Function (SMF), Policy Charging Function (PCF), Unified Data Management (UDM) and Operations, Administration and Management (OAM). For example, an AMF may request subscriber authentication data from an AUSF by calling a function in the API of an AUSF for this purpose. Efforts are being made to automate 5G networks, with the aim of providing fully automated wireless communication networks with zero touch (i.e. networks that require as little human intervention during operation as possible). One way of achieving this is to use the vast amounts of data collected in wireless communication networks in combination with machine-learning algorithms to develop models for use in providing network services. A Network Data Analytics (NWDA) framework has been established for defining the mechanisms and associated functions for data collection in 5G networks. Further enhancements to this framework are described in the 3GPP document TS 23.288 v 16.0.0. The NWDA framework is centred on a Network Data Analytics Function (NWDAF) that collects data from other network functions in the network. The NWDAF also provides services to service consumers (e.g. other network functions). The services include, for example, retrieving data or making predictions based on data collated at the NWDAF. Figure 1 shows an NWDAF 102 connected to a network function (NF) 104. As illustrated, the network function 104 may be any suitable network function (e.g. an AMF, an AUSF or any other network function). In order to collect data from the network function 104, the NWDAF 102 connects to an Event Exposure Function at the network function over an Nnf reference point (as detailed in the 3GPP documents TS 23.502 v 16.0.2 and TS 23.288 v 16.0.0). The NWDAF 102 can then receive data from the network function over the Nnf reference point by subscribing to reports from the network function or by requesting data from the network function. The timing of any reports may be determined by timeouts (e.g. expiry of a timer) or may be triggered by events (e.g. receipt of a request). The types of data that can be requested by the NWDAF 102 from the network function may be standardised. For the network function 104 to be discoverable by the NWDAF 102 (or any other service consumer such as, for example, another network function), the network function 104 registers with a Network function Repository Function (NRF). Figure 2 shows an illustration of an NRF 208 connected to three network functions, NF A 202, NF B 204 and NF C 206 that are registered at the NRF 208. The NRF 208 may be preconfigured with information about the network functions 202-206, or each of the network functions 202-206 may have performed a network registration procedure with the NRF 208 to register at the NRF 208. Once a network function is registered at the NRF 208, another entity in the network may discover the network function by calling a discovery function at the NRF 208. Thus, for example, NF B 204 may discover NF A 202 and NF C 206 by calling a discovery function at the NRF 208. As noted above, data collection has the potential to be a powerful tool for 5G networks when coupled with machine-learning. Machine-learning in the context of 5G networks is typically large-scale and may be executed in a cloud (virtualised) environment where performance and security are prioritised. In practice, this means that the data available for training models using machine-learning may be distributed across many entities in the network, and that data should ideally be collated at one network entity to be used for developing models using machine-learning. Collating these datasets at a single network entity can be slow and resource intensive, which is problematic for time-critical applications. In addition, some applications require the use of data sets comprising sensitive or private data, and collating these data at a single network entity may have security implications. Summary Embodiments of the disclosure address these and other problems. In one aspect