Revisiting Efficient Multi-Step Nonlinearity Compensation with Machine Learning: An Experimental Demonstration

TL;DR

This paper demonstrates that multi-step learned digital backpropagation can outperform traditional single-step methods in fiber-optic systems by carefully designing and jointly optimizing short, finite-impulse response filters, challenging the belief that fewer steps are always better.

Contribution

It provides an experimental demonstration of multi-step learned digital backpropagation in a real optical system, showing improved performance over standard methods with limited complexity.

Findings

LDBP outperforms standard DBP with short filters

Joint optimization of filters enhances performance

Multi-step approach challenges the single-step assumption

Abstract

Efficient nonlinearity compensation in fiber-optic communication systems is considered a key element to go beyond the "capacity crunch''. One guiding principle for previous work on the design of practical nonlinearity compensation schemes is that fewer steps lead to better systems. In this paper, we challenge this assumption and show how to carefully design multi-step approaches that provide better performance--complexity trade-offs than their few-step counterparts. We consider the recently proposed learned digital backpropagation (LDBP) approach, where the linear steps in the split-step method are re-interpreted as general linear functions, similar to the weight matrices in a deep neural network. Our main contribution lies in an experimental demonstration of this approach for a 25 Gbaud single-channel optical transmission system. It is shown how LDBP can be integrated into a coherent receiver DSP chain and successfully trained in the presence of various hardware impairments. Our results show that LDBP with limited complexity can achieve better performance than standard DBP by using very short, but jointly optimized, finite-impulse response filters in each step. This paper also provides an overview of recently proposed extensions of LDBP and we comment on potentially interesting avenues for future work.