Mobility handling of cross-node machine learning session in a radio access network
Certain aspects of the present disclosure provide techniques for handling user equipment (UE) mobility for a cross-node artificial intelligence (AI) and/or machine learning (ML) session in a radio access network (RAN). A method of wireless communication by a first network entity includes obtaining, from a second network entity, an indication of a handover for a UE; obtaining, from a third network entity, an indication of first cross-node machine learning information associated with a cross-node machine learning session between the UE and the third network entity; providing, to the second network entity, an indication acknowledging the handover; and relaying communications between the UE and the third network entity for the cross-node machine learning session.
1 . An apparatus configured for wireless communication, comprising one or more processors coupled to one or more memories, and configured to cause the apparatus to:
provide, to a first network entity, an indication of a handover for a user equipment (UE);
obtain an indication of first cross-node machine learning information associated with the first network entity; and
provide, to the UE, a handover command indicating the first cross-node machine learning information for a cross-node machine learning session between the UE and a second network entity.
2 . The apparatus of claim 1 , wherein:
to provide the indication of the handover, the one or more processors are configured to cause the apparatus to provide, to the first network entity, the indication of the handover via a handover request comprising second cross-node machine learning information associated with the apparatus; and
to obtain the indication of the first cross-node machine learning information, the one or more processors are configured to cause the apparatus to obtain, from the first network entity, the indication of the first cross-node machine learning information via a handover response.
3 . The apparatus of claim 2 , wherein:
the first cross-node machine learning information comprises one or more machine learning function names supported at the first network entity, and
the second cross-node machine learning information comprises one or more machine learning function names supported at the apparatus.
4 . The apparatus of claim 1 , wherein the one or more processors are configured to cause the apparatus to provide, to the second network entity, an indication of the handover for the UE associated with the cross-node machine learning session via a radio access network (RAN) intelligent controller (RIC) indication message.
5 . The apparatus of claim 1 , wherein to obtain the indication of the first cross-node machine learning information, the one or more processors are configured to cause the apparatus to obtain, from the second network entity, the indication of the first cross-node machine learning information via a radio access network (RAN) intelligent controller (RIC) control request message.
6 . The apparatus of claim 5 , wherein:
the RIC control request message comprises an indication of the first network entity being a target network entity for the handover associated with the UE; and
to provide the indication of the handover, the one or more processors are configured to cause the apparatus to provide, to the first network entity, the indication of the handover via a handover request in response to obtaining the indication of the first network entity being the target network entity for the handover.
7 . An apparatus configured for wireless communication, comprising one or more processors coupled to one or more memories, and configured to cause the apparatus to:
provide, to a first network entity, first signaling that controls a cross-node machine learning session between a user equipment (UE) and the apparatus;
provide, to a second network entity, an indication of first cross-node machine learning information associated with the cross-node machine learning session; and
provide, to the second network entity, second signaling that controls the cross-node machine learning session in response to a handover for the UE from the first network entity to the second network entity.
8 . The apparatus of claim 7 , wherein the second signaling indicates an update to a configuration used at the UE for the cross-node machine learning session.
9 . The apparatus of claim 7 , wherein:
the one or more processors are configured to cause the apparatus to obtain, from the first network entity, an indication of the handover for the UE associated with the cross-node machine learning session; and
to provide the indication of the first cross-node machine learning information, the one or more processors are configured to cause the apparatus to provide, to the second network entity, the indication of the first cross-node machine learning information via a radio access network (RAN) intelligent controller (RIC) subscription request message in response to obtaining the indication of the handover.
10 . The apparatus of claim 9 , wherein the indication of the handover comprises:
a first identifier associated with the UE, and
a second identifier associated with the second network entity being a target network entity for the handover.
11 . The apparatus of claim 7 , wherein the first cross-node machine learning information comprises one or more machine learning function names supported at the apparatus.
12 . The apparatus of claim 7 , wherein the one or more processors are configured to cause the apparatus to provide, to the first network entity, an indication of the second network entity being a target network entity for the handover associated with the UE.
13 . The apparatus of claim 12 , wherein to provide the indication of the second network entity being the target network entity, the one or more processors are configured to cause the apparatus to provide, to the first network entity, the indication of the second network entity being the target network entity via a radio access network (RAN) intelligent controller (RIC) control request.
14 . The apparatus of claim 7 , wherein:
the one or more processors are configured to cause the apparatus to obtain, from the second network entity, a request for the first cross-node machine learning information; and
to provide the indication of the first cross-node machine learning information, the one or more processors are configured to cause the apparatus to provide, to the second network entity, the indication of the first cross-node machine learning information in response to the request.
15 . The apparatus of claim 14 , wherein:
to obtain the request, the one or more processors are configured to cause the apparatus to obtain, from the second network entity, the request via a radio access network (RAN) intelligent controller (RIC) query message, the request comprising an indication of second cross-node machine learning information associated with the first network entity; and
to provide the indication of the first cross-node machine learning information, the one or more processors are configured to cause the apparatus to provide, to the second network entity, the indication of the first cross-node machine learning information via a RIC subscription request in response to the RIC query message.
16 . A method of wireless communication, comprising:
providing, to a first network entity, an indication of a handover for a user equipment (UE);
obtaining an indication of first cross-node machine learning information associated with the first network entity; and
providing, to the UE, a handover command indicating the first cross-node machine learning information for a cross-node machine learning session between the UE and a second network entity.
17 . The method of claim 16 , wherein:
providing the indication of the handover comprises providing, to the first network entity, the indication of the handover via a handover request comprising second cross-node machine learning information associated with the apparatus; and
obtaining the indication of the first cross-node machine learning information comprises obtaining, from the first network entity, the indication of the first cross-node machine learning information via a handover response.
18 . The method of claim 17 , wherein:
the first cross-node machine learning information comprises one or more machine learning function names supported at the first network entity, and
the second cross-node machine learning information comprises one or more machine learning function names supported at the apparatus.
19 . The method of claim 16 , wherein the method comprises providing, to the second network entity, an indication of the handover for the UE associated with the cross-node machine learning session via a radio access network (RAN) intelligent controller (RIC) indication message.
20 . The method of claim 16 , wherein obtaining the indication of the first cross-node machine learning information comprises obtaining, from the second network entity, the indication of the first cross-node machine learning information via a radio access network (RAN) intelligent controller (RIC) control request message.
21 . The method of claim 20 , wherein:
the RIC control request message comprises an indication of the first network entity being a target network entity for the handover associated with the UE; and
providing the indication of the handover comprises providing, to the first network entity, the indication of the handover via a handover request in response to obtaining the indication of the first network entity being the target network entity for the handover.
22 . A method of wireless communication, comprising:
providing, to a first network entity, first signaling that controls a cross-node machine learning session between a user equipment (UE) and the apparatus;
providing, to a second network entity, an indication of first cross-node machine learning information associated with the cross-node machine learning session; and
providing, to the second network entity, second signaling that controls the cross-node machine learning session in response to a handover for the UE from the first network entity to the second network entity.
23 . The method of claim 22 , wherein the second signaling indicates an update to a configuration used at the UE for the cross-node machine learning session.
24 . The method of claim 22 , wherein:
the method comprises obtaining, from the first network entity, an indication of the handover for the UE associated with the cross-node machine learning session; and
providing the indication of the first cross-node machine learning information comprises providing, to the second network entity, the indication of the first cross-node machine learning information via a radio access network (RAN) intelligent controller (RIC) subscription request message in response to obtaining the indication of the handover.
25 . The method of claim 24 , wherein the indication of the handover comprises:
a first identifier associated with the UE, and
a second identifier associated with the second network entity being a target network entity for the handover.
26 . The method of claim 22 , wherein the first cross-node machine learning information comprises one or more machine learning function names supported at the apparatus.
27 . The method of claim 22 , wherein the method comprises providing, to the first network entity, an indication of the second network entity being a target network entity for the handover associated with the UE.
28 . The method of claim 27 , wherein providing the indication of the second network entity being the target network entity comprises providing, to the first network entity, the indication of the second network entity being the target network entity via a radio access network (RAN) intelligent controller (RIC) control request.
29 . The method of claim 28 , wherein:
the method comprises obtaining, from the second network entity, a request for the first cross-node machine learning information; and
providing the indication of the first cross-node machine learning information comprises providing, to the second network entity, the indication of the first cross-node machine learning information in response to the request.
30 . The method of claim 29 , wherein:
obtaining the request comprises obtaining, from the second network entity, the request via a radio access network (RAN) intelligent controller (RIC) query message, the request comprising an indication of second cross-node machine learning information associated with the first network entity; and
providing the indication of the first cross-node machine learning information comprises providing, to the second network entity, the indication of the first cross-node machine learning information via a RIC subscription request in response to the RIC query message.