Method and apparatus for ai/ml based rrm including wide and fine beam searches

A user equipment (UE) to implement radio resource management (RRM) for the UE, the UE in connection with a base station, the UE comprising:

• at least one antenna;
• at least one radio, wherein the at least one radio is configured to communicate with the base station using the at least one antenna;
• and
• at least one processor coupled to the at least one radio, wherein the at least one processor is configured to perform operations comprising:
• selecting a sub-sample of beams received via the antenna from the base station;
• based on the selection of the sub-sample of beams, implementing an artificial intelligence/machine learning (AI/ML) model function to:
• generate a course training image map;
• generate a prediction image map from the course training image map;
• and
• select an optimal beam pair from the prediction image map for communication with the base station.

A non-transitory computer-readable storage medium, comprising instructions that, when executed by one or more processors of a user equipment (UE) in communication with a base station, cause the UE to:

• select a sub-sample of beams from the base station;
• and
• based on the selection of the sub-sample of beams, implement an artificial intelligence/machine learning (AI/ML) model function to:
• generate a course training image map;
• generate a prediction image map from the course training image map;
• and
• select an optimal beam pair from the prediction image map for communication with the base station.