Recursive Neural Network with Phase-Normalization for Modeling and Linearization of RF Power Amplifiers

This paper presents a novel Phase-Normalized Recurrent Neural Network (PN-RNN) to compensate the significant memory effects of RF power amplifiers in high- bandwidth communication systems.The proposed approach builds on proper phase alignment of the internal hidden variables in the recursive processing system.The provided RF measurement based modeling and digital predistortion results at 1.8\,GHz and 3.5\,GHz demonstrate a significantly improved modeling capacity and predistortion ability when applying phase normalization, confirming the validity of the proposed approach.