5G service based architecture (SBA) communication based on machine learning

1. A method, comprising:

receiving, by a network repository function (NRF), registration information of each of a plurality of network functions (NFs);

determining, by the NRF, load balance prioritization information for the plurality of NFs based on the received registration information;

detecting, by the NRF, whether a failure occurs in at least one of the plurality of NFs; and

in response to detecting a failure in at least one of the plurality of NFs:

transmitting, by the NRF to a Service Communication Proxy (SCP) with Machine Learning, the load balance prioritization information;

receiving, by a compute engine of an integration component, the load balance prioritization information from the NRF, the compute engine comprising a Machine Learning agent;

determining, by the compute engine comprising the Machine Learning agent, at least one load balance parameter based on the load balancing prioritization information; and

transmitting, by the integration component to a service mesh control plane, the at least one load balance parameter,

wherein the service mesh control plane is configured to perform load balancing on the plurality of NFs based on the at least one load balance parameter.

2. The method of claim 1 , wherein the plurality of NFs comprises at least one of an application management function (AMF), a session management function (SMF), a network slice selection function (NSSF), an authentication server function (AUSF), or a policy control function (PCF).

3. The method of claim 1 , wherein the registration information comprises information on at least one of an internet protocol (IP) address, location, priority, capacity, loading, or services of a NF.

4. The method of claim 1 , wherein the service mesh control plane is configured to perform load balancing on the plurality of NFs by a service mesh proxy on each of the plurality of NFs.

5. A system, comprising:

a plurality of network functions (NFs);

a network repository function (NRF); and

a service mesh control plane,

wherein the NRF is configured to:

receive registration information of each of the plurality of NFs;

determine load balance prioritization information for the plurality of NFs based on the received registration information;

detect whether a failure occurs in at least one of the plurality of NFs; and

in response to detecting a failure in at least one of the plurality of NFs, transmit, to Service Communication Proxy (SCP) with Machine Learning, the load balance prioritization information;

wherein the SCP with Machine Learning is configured to:

receive, by a compute engine of an integration component, the load balance prioritization information from the NRF, the compute engine comprising a Machine Learning agent;

determine, by the compute engine comprising the Machine Learning agent, at least one load balance parameter based on the load balancing prioritization information; and

transmit, by the integration component to the service mesh control plane, the at least one load balance parameter, and

wherein the service mesh control plane is configured to perform load balancing on the plurality of NFs based on the at least one load balance parameter.

6. The system of claim 5 , wherein the plurality of NFs comprises at least one of an application management function (AMF), a session management function (SMF), a network slice selection function (NSSF), an authentication server function (AUSF), or a policy control function (PCF).

7. The system of claim 5 , wherein the registration information comprises information on at least one of an internet protocol (IP) address, location, priority, capacity, loading, or services of a NF.

8. The system of claim 5 , wherein the service mesh control plane is further configured to perform load balancing on the plurality of NFs by a service mesh proxy on each of the plurality of NFs.

9. A non-transitory computer readable storage medium, the storage medium connected to one or more processors and storing instructions that, when executed, cause the one or more processors to:

receive, by a network repository function (NRF), registration information of each of a plurality of network functions (NFs);

determine, by the NRF, load balance prioritization information for the plurality of NFs based on the received registration information;

detect, by the NRF, whether a failure occurs in at least one of the plurality of NFs; and

in response to detecting a failure in at least one of the plurality of NFs:

transmit, by the NRF to a Service Communication Proxy (SCP) with Machine Learning, the load balance prioritization information;

receive, by a compute engine of an integration component, the load balance prioritization information from the NRF, the compute engine comprising a Machine Learning agent;

determine, by the compute engine comprising the Machine Learning agent, at least one load balance parameter based on the load balancing prioritization information; and

transmit, by the integration component to a service mesh control plane, the at least one load balance parameter,

wherein the service mesh control plane is configured to perform load balancing on the plurality of NFs based on the at least one load balance parameter.

10. The storage medium of claim 9 , wherein the plurality of NFs comprises at least one of an application management function (AMF), a session management function (SMF), a network slice selection function (NSSF), an authentication server function (AUSF), or a policy control function (PCF).

11. The storage medium of claim 9 , wherein the registration information comprises information on at least one of an internet protocol (IP) address, location, priority, capacity, loading, or services of a NF.