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

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.

Submitted to ECOC post-deadline, Sep. 2019, Dublin, Ireland