Applying conditions for input parameters for UE-Sided prediction using an ML model

Abstract

A second network node, e.g. user equipment (UE) 10, receives from a first network node, e.g. base station 70, configuration 325 for performing prediction, e.g. cell or beam prediction, by a machine-learning (ML) model including input condition(s), e.g. cell quality or beam quality, related to input parameters, e.g. cell quality values or beam quality values, for the ML model. The second network node, e.g. UE 10, determines 321 whether input parameters for the ML model do or do not fulfill the input condition(s). Responsive to the determining, the second network node, e.g. UE 10, performs one or both of prediction using the ML model or reporting 340 to the first network node, e.g. base station 70, of information 345 based on whether or not the prediction was performed. The first network node, e.g. base station 70, receives one or both of the output 330 of the prediction performed using the ML model on the second network node, e.g. UE 10, or the information 345 based on whether or not the prediction was performed.

Images