NN-Based Frequency Domain DPD for OFDM Massive MIMO Transmitters With Multiple States

TL;DR

This paper introduces a neural network-based frequency domain digital predistortion method for massive MIMO transmitters that adapts to multiple signal states without additional online training, enhancing efficiency.

Contribution

It proposes a novel NN-based FD-DPD model utilizing a hypernetwork to generate output layer parameters based on signal states, extending FD-DPD to multi-state scenarios.

Findings

Achieves excellent performance in simulations

Does not require online retraining when signal states change

Effective for bandwidth and power level variations

Abstract

Frequency domain (FD)-digital predistortion (DPD) is a low-complexity DPD solution for massive multiple-inputmultiple-output (MIMO) transmitters (TXs). In this letter, we extend FD-DPD to scenarios with multiple signal states (e.g., bandwidths and power levels). First, we propose a new neural network (NN)-based FD-DPD model, whose main idea is to use a hypernetwork (HN) to generate parameters for the output layer of the main NN based on the signal states. Then, we introduce how to effectively train the model with the help of time-domain (TD)-DPD. Experimental results show that the proposed model can achieve excellent performance, without requiring additional online training when signal states change.