Neural Networks-based Equalizers for Coherent Optical Transmission: Caveats and Pitfalls

TL;DR

This paper critically analyzes the challenges and pitfalls in designing neural network-based equalizers for coherent optical systems, providing guidance on metrics, model accuracy, data limitations, overfitting, and complexity evaluation.

Contribution

It offers a comprehensive analysis of design caveats and provides analytical tools for evaluating neural network equalizers in optical communications.

Findings

Metrics are closely related to training loss functions.

Channel model accuracy significantly impacts equalizer performance.

Overfitting and data limitations are critical challenges.

Abstract

This paper performs a detailed, multi-faceted analysis of key challenges and common design caveats related to the development of efficient neural networks (NN) nonlinear channel equalizers in coherent optical communication systems. Our study aims to guide researchers and engineers working in this field. We start by clarifying the metrics used to evaluate the equalizers' performance, relating them to the loss functions employed in the training of the NN equalizers. The relationships between the channel propagation model's accuracy and the performance of the equalizers are addressed and quantified. Next, we assess the impact of the order of the pseudo-random bit sequence used to generate the -- numerical and experimental -- data as well as of the DAC memory limitations on the operation of the NN equalizers both during the training and validation phases. Finally, we examine the critical issues of overfitting limitations, the difference between using classification instead of regression, and batch-size-related peculiarities. We conclude by providing analytical expressions for the equalizers' complexity evaluation in the digital signal processing (DSP) terms and relate the metrics to the processing latency.