Supporting multiple application function sessions with required group quality of service (QoS) provided by machine learning model provider application function
Embodiments herein provide techniques related to a NEF. An example technique includes identifying, from an AF that implements a ML model, a request related to reservation of resources for a plurality of AF sessions, wherein the plurality of AF sessions relate to respective UEs of a plurality of UEs, and wherein the request includes an indication of addresses of respective UEs of the plurality of UEs and a QoS parameter; transmitting, to a BSF of the cellular network, a discovery request related to discovery of respective PCFs that are serving the respective UEs of the plurality of UEs; identifying, based on the discovery request, a discovery response that includes indications of the PCFs; identifying, based on the indications of the PCFs and the QoS parameter, a result related to the reservation of resources; and transmitting, to the AF, an indication of the result. Other embodiments may be described and/or claimed.
1. One or more non-transitory computer-readable media (NTCRM) comprising instructions that, when executed by one or more processors of an electronic device, are to cause a network exposure function (NEF) of a cellular network to:
identify, from an application function (AF) that implements a machine learning (ML) model, a request related to reservation of resources for a plurality of AF sessions, wherein the plurality of AF sessions relate to respective user equipments (UEs) of a plurality of UEs, and wherein the request includes an indication of addresses of respective UEs of the plurality of UEs and a quality of service (QoS) parameter;
transmit, to a binding support function (BSF) of the cellular network, a discovery request related to discovery of respective policy control functions (PCFs) that are serving the respective UEs of the plurality of UEs;
identify, based on the discovery request, a discovery response that includes indications of the PCFs;
identify, based on the indications of the PCFs and the QoS parameter, a result related to the reservation of resources; and
transmit, to the AF, an indication of the result.
2. The one or more NTCRM of claim 1 , wherein the request related to reservation of resources is a Nnef_GroupAFsessionWithQoS_Create request message.
3. The one or more NTCRM of claim 1 , wherein the discovery request is a Nbsf_Management_Discovery request message.
4. The one or more NTCRM of claim 1 , wherein the discovery response is a Nbsf_Management_Discovery response message.
5. The one or more NTCRM of claim 1 , wherein the result is granting the request related to reservation of resources if a number of UEs of the plurality of UEs that are associated with a PCF that meets the QoS parameter is greater than a threshold number.
6. The one or more NTCRM of claim 1 , wherein the result is declining the request related to reservation of resources if a number of UEs of the plurality of UEs that are associated with a PCF that meets the QoS parameter is less than the threshold number.
7. The one or more NTCRM of claim 1 , wherein the request related to reservation of resources further includes an indication of a time period related to the QoS parameter.
8. The one or more NTCRM of claim 7 , wherein the time period related to the QoS parameter is based on a determination by a machine learning (ML) model of the AF that is related to tolerance for UE dropout.
9. The one or more NTCRM of claim 7 , wherein the request related to reservation of resources includes: an External Group identifier (ID), an indication of a wireless link condition threshold, an indication of a deadline for parameter update, an indication of quality of data, an indication of traffic volume for the requested QoS, an an indication of a threshold number related to a minimum UEs in the group with the requested QoS.
10. An electronic device comprising:
one or more processors to implement a network exposure function (NEF) of a cellular network; and
one or more non-transitory computer-readable media (NTCRM) comprising instructions that, when executed by the one or more processors, are to cause the NEF to:
identify, from an application function (AF) that implements a machine learning (ML) model, a request related to reservation of resources for a plurality of AF sessions, wherein the plurality of AF sessions relate to respective user equipments (UEs) of a plurality of UEs, and wherein the request includes an indication of addresses of respective UEs of the plurality of UEs and a quality of service (QoS) parameter;
transmit, to a binding support function (BSF) of the cellular network, a discovery request related to discovery of respective policy control functions (PCFs) that are serving the respective UEs of the plurality of UEs;
identify, based on the discovery request, a discovery response that includes indications of the PCFs;
identify, based on the indications of the PCFs and the QoS parameter, a result related to the reservation of resources; and
transmit, to the AF, an indication of the result.
11. The electronic device of claim 10 , wherein the request related to reservation of resources is a Nnef_GroupAFsessionWithQoS_Create request message.
12. The electronic device of claim 10 , wherein the discovery request is a Nbsf_Management_Discovery request message.
13. The electronic device of claim 10 , wherein the discovery response is a Nbsf_Management_Discovery response message.
14. The electronic device of claim 10 , wherein the result is granting the request related to reservation of resources if a number of UEs of the plurality of UEs that are associated with a PCF that meets the QoS parameter is greater than a threshold number.
15. The electronic device of claim 10 , wherein the result is declining the request related to reservation of resources if a number of UEs of the plurality of UEs that are associated with a PCF that meets the QoS parameter is less than the threshold number.
16. The electronic device of claim 10 , wherein the request related to reservation of resources further includes an indication of a time period related to the QoS parameter.
17. A method to be performed by a network exposure function (NEF) of a cellular network, wherein the method comprises:
identifying, from an application function (AF) that implements a machine learning (ML) model, a request related to reservation of resources for a plurality of AF sessions, wherein the plurality of AF sessions relate to respective user equipments (UEs) of a plurality of UEs, and wherein the request includes an indication of addresses of respective UEs of the plurality of UEs and a quality of service (QoS) parameter;
transmitting, to a binding support function (BSF) of the cellular network, a discovery request related to discovery of respective policy control functions (PCFs) that are serving the respective UEs of the plurality of UEs;
identifying, based on the discovery request, a discovery response that includes indications of the PCFs;
identifying, based on the indications of the PCFs and the QoS parameter, a result related to the reservation of resources; and
transmitting, to the AF, an indication of the result.
18. The method of claim 17 , wherein the request related to reservation of resources is a Nnef_GroupAFsessionWithQoS_Create request message.
19. The method of claim 17 , wherein the discovery request is a Nbsf_Management_Discovery request message.
20. The method of claim 17 , wherein the discovery response is a Nbsf_Management_Discovery response message.