Soft-Demapping for Short Reach Optical Communication: A Comparison of Deep Neural Networks and Volterra Series

TL;DR

This paper compares deep neural networks and Volterra series for nonlinear equalization in short reach optical communication, demonstrating that DNNs can achieve similar or better performance with significantly reduced complexity.

Contribution

It introduces a soft DNN equalizer as an alternative to Volterra series, showing improved efficiency and performance in optical signal processing.

Findings

DNN equalizer reduces complexity by 65% compared to Volterra.

At equal performance, DNN achieves 0.35 dB OSNR gain.

DNN outperforms Volterra in nonlinear equalization tasks.

Abstract

In optical fiber communication, optical and electrical components introduce nonlinearities, which require effective compensation to attain highest data rates. In particular, in short reach communication, components are the dominant source of nonlinearities. Volterra series are a popular countermeasure for receiver-side equalization of nonlinear component impairments and their memory effects. However, Volterra equalizer architectures are generally very complex. This article investigates soft deep neural network (DNN) architectures as an alternative for nonlinear equalization and soft-decision demapping. On coherent 92 GBd dual polarization 64QAM back-to-back measurements performance and complexity is experimentally evaluated. The proposed bit-wise soft DNN equalizer (SDNNE) is compared to a 5th order Volterra equalizer at a 15 % overhead forward error correction (FEC) limit. At equal performance, the computational complexity is reduced by 65 %. At equal complexity, the performance is improved by 0.35 dB gain in optical signal-to-noise-ratio (OSNR).