Real-Time Machine Learning Based Fiber-Induced Nonlinearity Compensation in Energy-Efficient Coherent Optical Networks

TL;DR

This paper presents a real-time fiber nonlinearity compensator using FPGA and machine learning, significantly improving signal quality in optical networks.

Contribution

It introduces the first FPGA-based real-time NLC using sparse K-means++ clustering in a high-speed optical system, enhancing energy efficiency and performance.

Findings

Up to 3 dB Q-factor improvement over linear equalization

Successful implementation of real-time NLC in a 40-Gb/s system

Energy-efficient fiber nonlinearity compensation demonstrated

Abstract

We experimentally demonstrate the first field-programmable gate-array-based real-time fiber nonlinearity compensator (NLC) using sparse K-means++ machine learning clustering in an energy-efficient 40-Gb/s 16-quadrature amplitude modulated self-coherent optical system. Our real-time NLC shows up to 3 dB improvement in Q-factor compared to linear equalization at 50 km of transmission.