Multi-Output Recurrent Neural Network Behavioral Model for Digital Predistortion of RF Power Amplifiers

DOI number:10.1109/LMWT.2023.3263642

Affiliation of Author(s):中国科学技术大学

Teaching and Research Group:电子工程与信息科学系

Journal:IEEE Microwave and Wireless Technology Letters

Key Words:Behavioral modeling, digital predistortion (DPD), long short-term memory (LSTM), multi-output neural network (NN), power amplifiers (PAs)

Abstract:In this letter, we propose a method for behavioral modeling and digital predistortion (DPD) of RF power amplifiers (PAs) based on multi-output recurrent neural networks (RNNs). RNN has high modeling accuracy, but it also has high running complexity due to the recurrent mechanism. For this reason, we propose a multi-output model architecture, which means that the DPD model produces multiple adjacent outputs simultaneously for a single input sample group. This approach greatly reduces the running complexity of DPD based on RNNs with essentially no deterioration in performance. The proposed multi-output mechanism is applied to both long short-term memory (LSTM) and gate recurrent unit (GRU), and excellent linearization performances are maintained.

First Author:Qianqian Zhang (张牵牵)

Co-author:Chengye Jiang,Guichen Yang,Renlong Han

Indexed by:Journal paper

Correspondence Author:Falin Liu

Discipline:Engineering

Document Type:J

Volume:33

Issue:7

Page Number:1067-1070

Translation or Not:no

Date of Publication:2023-07-07

Included Journals:SCI、EI