Exceeding the Nonlinear Shannon-Limit in Coherent Optical Communications by MIMO Machine Learning

TL;DR

This paper introduces a MIMO deep neural network approach that surpasses the nonlinear Shannon limit in coherent optical communications by effectively compensating for both deterministic and stochastic fiber nonlinearities, achieving record transmission performance.

Contribution

The paper presents a novel MIMO deep learning method that jointly addresses deterministic and stochastic nonlinearities in optical signals, outperforming traditional equalizers.

Findings

Achieved record-breaking transmission at 40 Gbit/sec.

Significantly outperforms conventional machine learning methods.

Effectively compensates for nonlinear inter-carrier crosstalk and stochastic variations.

Abstract

The nonlinear Shannon capacity limit has been identified as the fundamental barrier to the maximum rate of transmitted information in optical communications. In long-haul high-bandwidth optical networks, this limit is mainly attributed to deterministic Kerr-induced fiber nonlinearities and from the interaction of amplified spontaneous emission noise from cascaded optical amplifiers with fiber nonlinearity: the stochastic parametric noise amplification. Unlike earlier impractical approaches that compensate solely deterministic nonlinearities, here we demonstrate a novel electronic-based deep neural network with multiple-inputs and outputs (MIMO) that tackles the interplay of deterministic and stochastic nonlinearity manifestation in coherent optical signals. Our demonstration shows that MIMO deep learning can compensate nonlinear inter-carrier crosstalk effects even in the presence of frequency stochastic variations, which has hitherto been considered impossible. Our solution significantly outperforms conventional machine learning and gold-standard nonlinear equalizers without sacrificing computational complexity, leading to record-breaking transmission performance for up to 40 Gbit/sec high-spectral-efficient optical signals.