Implementing distributed computation for precoding in mu-mimo

Abstract

Distributed precoding computation involves receiving, from UEs served by the base station, UE precoding capability information for UE support of distributed iterative precoding computation or distributed artificial intelligence (AI)-based precoding computation. A precoding computation scheme is determined based on the UE precoding capability information and UE characteristics. Results of local precoding computations by each of the UEs are employed in determining precoders for the UEs. Distributed precoding computation parameters are transmitted to the UEs. The parameters may enable/disable distributed precoding computation, identify a precoding algorithm, or indicate a number of iterations or a maximum iteration time for precoding computation, and the results of local precoding computations may include an updated result after a specific iteration. For a transformer-based distributed precoding computation algorithm, the distributed precoding computation parameters may indicate trained neural network parameters and the results of local precoding computations may include an output of a neural network encoder.

Dependencies are inferred from the claim text.