Low Noise Non-Linear Equalization Using Neural Networks and Belief Propagation

TL;DR

This paper introduces a novel nonlinear equalization method combining neural networks and belief propagation, effectively balancing distortion reduction and noise enhancement in communication systems, resulting in significant performance gains.

Contribution

It proposes a new hybrid nonlinear equalization approach that alternates between neural networks and belief propagation, improving noise mitigation and nonlinearity compensation.

Findings

Achieves a 0.6 dB gain over Volterra equalizer with optimal training SNR.

Attains a 1.7 dB gain compared to systems without nonlinearity compensation.

Provides a method to optimize training SNR for better trade-offs.

Abstract

Nonlinearities can be introduced into communication systems by the physical components such as the power amplifier, or during signal propagation through a nonlinear channel. These nonlinearities can be compensated by a nonlinear equalizer at the receiver side. The nonlinear equalizer also operates on the additive noise, which can lead to noise enhancement. In this work we evaluate this trade-off between distortion reduction and noise-enhancement via nonlinear equalization techniques. We first, evaluate the trade-off between nonlinearity compensation and noise enhancement for the Volterra equalizer, and propose a method to determine the training SNR that optimizes this performance trade-off. We then propose a new approach for nonlinear equalization that alternates between neural networks (NNs) for nonlinearity compensation, and belief propagation (BP) for noise removal. This new approach achieves a 0.6 dB gain compared to the Volterra equalizer with the optimal training SNR, and a 1.7 dB gain compared to a system with no nonlinearity compensation.