Multichannel Nonlinear Equalization in Coherent WDM Systems based on Bi-directional Recurrent Neural Networks

TL;DR

This paper introduces a bidirectional recurrent neural network for multichannel nonlinear equalization in WDM optical systems, achieving significant OSNR gains and complexity reduction compared to traditional methods.

Contribution

It presents a novel multi-channel bidirectional RNN approach that outperforms single-channel RNN and digital back-propagation in nonlinear equalization of WDM signals.

Findings

Over 2.5 dB OSNR gain demonstrated

Up to 43% complexity reduction achieved

Effective in experimental QPSK metro link

Abstract

Kerr nonlinearity in the form of self- and cross-phase modulation imposes a fundamental limitation to the capacity of wavelength division multiplexed (WDM) optical communication systems. Digital back-propagation (DBP), that requires solving the inverse-propagating nonlinear Schr\"odinger equation (NLSE), is a widely adopted technique for the mitigation of impairments induced by Kerr nonlinearity. However, multi-channel DBP is too complex to be implemented commercially in WDM systems. Recurrent neural networks (RNNs) have been recently exploited for nonlinear signal processing in the context of optical communications. In this work, we propose multi-channel equalization through a bidirectional vanilla recurrent neural network (bi-VRNN) in order to improve the performance of the single-channel bi-VRNN algorithm in the transmission of WDM M-QAM signals. We compare the proposed digital algorithm to full-field DBP and to the single channel bi-RNN in order to reveal its merits with respect to both performance and complexity. We finally provide experimental verification through a QPSK metro link, showcasing over 2.5 dB optical signal-to-noise ratio (OSNR) gain and up to 43% complexity reduction with respect to the single-channel RNN and the DBP.