Methods, apparatus and machine-readable media relating to machine-learning in a communication network
A method performed by a co-ordination network entity in a communications network includes transmitting a request message to a network registration entity in the communications network for identification information for a plurality of candidate network entities in the communications network capable of performing collaborative learning, and receiving identification information for the plurality of candidate network entities from the network registration entity. The method further includes initiating, at one or more network entities of the plurality of candidate network entities, training of a model using a machine-learning algorithm as part of a collaborative learning process.
1. A method performed by a co-ordination network entity in a communications network, the method comprising:
transmitting a first request message, from the co-ordination network entity to a network registration entity in the communications network, for identification information for a plurality of candidate network entities in the communications network capable of performing collaborative learning;
receiving, at the co-ordination network entity, identification information for a plurality of candidate network entities from the network registration entity;
transmit a second request message comprising at least one query for additional information for the plurality of candidate network entities;
select, based on one or more responses to the at least one query, one or more network entities from the plurality of candidate network entities; and
initiating, at the selected one or more network entities from the plurality of candidate network entities, training of a model using a machine-learning algorithm as part of a collaborative learning process.
2. The method of claim 1 , wherein the co-ordination network entity is a network data analytics function, NWDAF.
3. The method of claim 1 , wherein the network registration entity is a network function repository function, NRF.
4. A co-ordination network entity for a communications network, the co-ordination network entity comprising processing circuitry and a non-transitory machine-readable medium storing instructions which, when executed by the processing circuitry, cause the co-ordination network entity to:
transmit a first request message, from the co-ordination network entity to a network registration entity in the communications network, for identification information for a plurality of candidate network entities in the communications network capable of performing collaborative learning;
receive, at the co-ordination network entity, identification information for a plurality of candidate network entities from the network registration entity;
transmit a second request message comprising at least one query for additional information for the plurality of candidate network entities;
select, based on one or more responses to the at least one query, one or more network entities from the plurality of candidate network entities; and
initiate, at the selected one or more network entities from the plurality of candidate network entities, training of a model using a machine-learning algorithm as part of a collaborative learning process.
5. The co-ordination network entity of claim 4 , wherein the request message comprises one or more criteria for selecting candidate network entities for performing the collaborative learning process.
6. The co-ordination network entity of claim 5 , wherein the one or more criteria comprise one or more of:
at least one primary criterion relating to a capability of the candidate network entity to perform the collaborative learning process; and
at least one secondary criterion relating to a capability of the candidate network entity to respond to a type of query.
7. The co-ordination network entity of claim 4 , wherein the at least one query for additional information relates to one or more of the following:
a configuration of the candidate network entity;
a performance requirement for the candidate network entity;
an availability of training data at the candidate network entity for training the model; and
a property of training data available at the candidate network entity.
8. The co-ordination network entity of claim 4 , wherein one or more of the following applies:
the co-ordination network entity is a network data analytics function, NWDAF; and
the network registration entity is a network function repository function, NRF.
9. The co-ordination network entity of claim 4 , wherein one or more of the co-ordination network entity and the network registration entity are in a core network of the communications network.
10. A network registration entity for a communications network, the network registration entity comprising processing circuitry and a non-transitory machine-readable medium storing instructions which, when executed by the processing circuitry, cause the network registration entity to:
receive, at the network registration entity, a request message from a co-ordination network entity in the communications network, the request message comprises one or more criteria for selecting a candidate network entity from the plurality of network entities for training a model using a machine-learning algorithm as part of a collaborative learning process;
identify, from a plurality of network entities registered at the network registration entity, two or more candidate network entities that satisfy the one or more criteria;
store capability information, for each network entity in the plurality of candidate network entities registered at the network registration entity, comprising an indication of whether or not the network entity is configured to respond to a type of query; and
transmit, from the network registration entity, an indication of the two or more candidate network entities to the co-ordination network entity.
11. The network registration entity of claim 10 , wherein the one or more criteria comprise one or more of:
at least one primary criterion relating to a capability of the candidate network entity to perform the collaborative learning process; and
at least one secondary criterion relating to a capability of the candidate network entity to respond to a type of query.
12. The network registration entity of claim 11 , wherein the type of query includes one or more of the following:
a query related to a configuration of the candidate network entity;
a query related to a performance requirement for the candidate network entity;
a query related to an availability of training data at the candidate network entity for training the model; and
a query related to a property of training data available at the candidate network entity.
13. The network registration entity of claim 10 , wherein the stored capability information is stored in a profile for each network entity in the plurality network entities registered at the network registration entity.
14. The network registration entity of claim 13 , wherein, for each network entity, the stored capability information further comprises an indication of whether or not the network entity is capable of performing collaborative learning.
15. The network registration entity of claim 10 , wherein one or more of the following applies:
the network registration entity is a network function repository function, NRF; and
the co-ordination network entity is a network data analytics function, NWDAF.
16. The network registration entity of claim 10 , wherein one or more of the network registration entity and the co-ordination network entity are in a core network of the communications network.
17. A system in a communications network, the system comprising a co-ordination network entity and a network registration entity, wherein the network registration entity comprises first processing circuitry and a first non-transitory machine-readable medium storing instructions which, when executed by the first processing circuitry, cause the network registration entity to:
receive a request message, at the network registration entity from the co-ordination network entity, the request message requesting identification information for a plurality of candidate network entities in the communications network capable of performing collaborative learning, and
identify, from a plurality of network entities registered at the network registration entity, two or more candidate network entities capable of performing collaborative learning;
store capability information, for each network entity in the plurality of candidate network entities registered at the network registration entity, comprising an indication of whether or not the network entity is configured to respond to a type of query; and
wherein the co-ordination network entity comprises second processing circuitry and a second non-transitory machine-readable medium storing instructions which, when executed by the second processing circuitry, cause the co-ordination network entity to:
receive, at the co-ordination network entity, identification information for the two or more candidate network entities from the network registration entity, and
initiate, at one or more network entities of the two or more candidate network entities, training of a model using a machine-learning algorithm as part of a collaborative learning process.
18. The network registration entity of claim 10 , wherein the one or more criteria comprise at least one primary criterion relating to a capability of the candidate network entity to perform the collaborative learning process.
19. The network registration entity of claim 11 , wherein the type of query includes one or more of the following:
a query related to an availability of training data at the candidate network entity for training the model; and
a query related to a property of training data available at the candidate network entity.