Low Complexity Joint Impairment Mitigation of I/Q Modulator and PA Using Neural Networks

TL;DR

This paper introduces two low-complexity neural network methods, ARDEN and pruning, for joint impairment mitigation in direct conversion transmitters, effectively compensating hardware impairments with reduced computational demands.

Contribution

The paper presents a novel attention residual neural network and a pruning algorithm that together reduce complexity while maintaining high performance in hardware impairment mitigation.

Findings

ARDEN with pruning outperforms existing NN and Volterra models in impairment compensation.

The proposed methods achieve better performance with less or similar complexity.

Simulation and experimental results validate the effectiveness of the approach.

Abstract

Neural networks (NNs) for multiple hardware impairments mitigation of a realistic direct conversion transmitter are impractical due to high computational complexity. We propose two methods to reduce complexity without significant performance penalty. We first propose a novel attention residual learning NN, referred to as attention residual real-valued time-delay neural network (ARDEN), where trainable neuron-wise shortcut connections between the input and output layers allow to keep the attention always active. Furthermore, we implement a NN pruning algorithm that gradually removes connections corresponding to minimal weight magnitudes in each layer. Simulation and experimental results show that ARDEN with pruning achieves better performance for compensating frequency-dependent quadrature imbalance and power amplifier nonlinearity than other NN-based and Volterra-based models, while requiring less or similar complexity.