Resource allocation and activation/deactivation configuration of open radio access network (O-RAN) network slice subnets

1. An apparatus for a Non-Real-Time RAN Intelligent Controller (Non-RT RIC) of a Service Management and Orchestration (SMO) entity of an Open Radio Access Network (O-RAN), the apparatus comprising:

processing circuitry, wherein to configure the Non-RT RIC for allocation of network slice subnet instance (NSSI) resources in the O-RAN, the processing circuitry is to:

collect performance measurements related to usage of the NSSI resources;

train an artificial intelligence (AI)/machine learning (ML) model based on the performance measurements; and

optimize the allocation of the NSSI resources at a particular time and a particular O-RAN node of the O-RAN, the particular time and the particular O-RAN node determined by an inference of the AI/ML model; and

a memory coupled to the processing circuitry and configured to store the performance measurements.

2. The apparatus of claim 1 , wherein the processing circuitry is further to:

train the AI/ML model based on the performance measurements, to predict traffic demand patterns of a NSSI associated with the NSSI resources at the time determined by the inference.

3. The apparatus of claim 2 , wherein the NSSI is activated by a network slice subnet management service provider (NSSMS_P) of the O-RAN based on a request from a network slice subnet management service consumer (NSSMS_C).

4. The apparatus of claim 1 , wherein to optimize the allocation of the NSSI resources the processing circuitry is further to:

reconfigure at least one NSSI attribute of a NSSI using the NSSI resources via an O1 interface with an O-RAN node.

5. The apparatus of claim 4 , wherein to optimize the allocation of the NSSI resources the processing circuitry is further to:

update cloud resources of a cloud of the O-RAN (O-Cloud) via an O2 interface between the Non-RT RIC and the O-Cloud.

6. The apparatus of claim 1 , wherein the NSSI resources include at least one of:

the time determined by the inference;

a location of a RAN node associated with the O-RAN;

a NSSI ID;

one or more slice subnet attributes; and

virtualized network function (VNF) resources update.

7. The apparatus of claim 1 , wherein the processing circuitry is further to:

train the AI/ML model based on the performance measurements, to predict traffic demand patterns of a NSSI associated with the NSSI resources at the time determined by the inference; and

reconfigure at least one NSSI attribute of a NSSI using the NSSI resources via an O1 interface with an O-RAN node and update cloud resources of a cloud of the O-RAN (O-Cloud) via an O2 interface between the Non-RT RIC and the O-Cloud to optimize the allocation of the NSSI resources, wherein the NSSI resources include at least one of:

the time determined by the inference;

a location of a RAN node associated with the O-RAN;

a NSSI ID;

one or more slice subnet attributes; and

virtualized network function (VNF) resources update.

8. The apparatus of claim 1 , wherein the performance measurements include one or more of:

downlink (DL) physical resource blocks (PRBs) used for data traffic;

uplink (UL) PRBs used for data traffic;

an average DL user equipment (UE) throughput in a next generation Node-B (gNB) of the O-RAN;

an average UL UE throughput in the gNB;

a number of protocol data unit (PDU) sessions requested for setup in the O-RAN;

a number of PDU sessions successfully set up in the O-RAN; and

a number of PDU sessions failed to set up in the O-RAN.

9. The apparatus of claim 1 , wherein the performance measurements are received from a plurality of O-RAN nodes, the plurality of O-RAN nodes including one or more of:

an O-RAN Central Unit-Control Plane (O-CU-CP) node;

an O-RAN Central Unit-User Plane (O-CU-UP) node;

an O-RAN Distributed Unit (a-DU) node; and

an O-RAN Radio Unit (O-RU) node.

10. The apparatus of claim 1 , wherein the processing circuitry is to:

generate an instruction for execution by an O-Cloud Management and Orchestration node, the execution of the instruction causing an update of the NSSI resources.

11. A non-transitory computer-readable storage medium that stores instructions for execution by one or more processors of a Non-Real-Time RAN Intelligent Controller (Non-RT RIC) of a Service Management and Orchestration (SMO) entity of an Open Radio Access Network (O-RAN), the instructions to configure the Non-RT RIC for allocation of network slice subnet instance (NSSI) resources in the O-RAN, and to cause the Non-RT MC to perform operations comprising:

collecting performance measurements related to usage of the NSSI resources;

training an artificial intelligence (AI)/machine learning (ML) model based on the performance measurements; and

optimizing the allocation of the NSSI resources at a particular time and a particular O-RAN node of the O-RAN, the particular time and the particular O-RAN node determined by an inference of the AI/ML model.

12. The non-transitory computer-readable storage medium of claim 11 , the operations further comprising:

training the AI/ML model based on the performance measurements, to predict traffic demand patterns of a NSSI associated with the NSSI resources at the time determined by the inference.

13. The non-transitory computer-readable storage medium of claim 11 , wherein the operations for optimizing the allocation of the NSSI resources further comprise:

reconfiguring at least one NSSI attribute of a NSSI using the NSSI resources via an O1 interface with an O-RAN node.

14. The non-transitory computer-readable storage medium of claim 13 , wherein the operations for optimizing the allocation of the NSSI resources further comprise:

updating cloud resources of a cloud of the O-RAN (O-Cloud) via an O2 interface between the Non-RT RIC and the O-Cloud.

15. The non-transitory computer-readable storage medium of claim 11 , wherein the NSSI resources include at least one of:

the time determined by the inference;

a location of a RAN node associated with the O-RAN;

a NSSI ID;

one or more slice subnet attributes; and

virtualized network function (VNF) resources update.

16. A system comprising:

a Service Management and Orchestration (SMO) entity of an Open Radio Access Network (O-RAN);

a Non-Real-Time RAN Intelligent Controller (Non-RT RIC) coupled to the SMO entity; and

processing circuitry coupled to a RAN node of the O-RAN via an O1 interface and a cloud of the O-RAN (O-Cloud) via an O2 interface, wherein to configure the Non-RT RIC for allocation of network slice subnet instance (NSSI) resources in the O-RAN, the processing circuitry to:

collect performance measurements related to usage of the NSSI resources;

train an artificial intelligence (AI)/machine learning (ML) model based on the performance measurements; and

optimize the allocation of the NSSI resources at a particular time and a particular O-RAN node of the O-RAN, the particular time and the particular O-RAN node determined by an inference of the AI/ML model.

17. The system of claim 16 , wherein the processing circuitry is further to:

train the AI/ML model based on the performance measurements, to predict traffic demand patterns of a NSSI associated with the NSSI resources at the time determined by the inference.

18. The system of claim 16 , wherein to optimize the allocation of the NSSI resources the processing circuitry is further to:

reconfigure at least one NSSI attribute of a NSSI using the NSSI resources via an O1 interface with an O-RAN node.

19. The system of claim 18 , wherein to optimize the allocation of the NSSI resources the processing circuitry is further to:

update cloud resources of a cloud of the O-RAN (O-Cloud) via an O2 interface between the Non-RT RIC and the O-Cloud.

20. The system of claim 16 , wherein the NSSI resources include at least one of:

the time determined by the inference;

a location of a RAN node associated with the O-RAN;

a NSSI ID;

one or more slice subnet attributes; and

virtualized network function (VNF) resources update.