Real-time machine learning based fiber-induced nonlinearity compensation in energy-efficient coherent optical networks

Elias Giacoumidis; Yi Lin; Michaela Blott; Liam P. Barry

doi:10.1063/1.5140609

APL Photonics (Apr 2020)

Real-time machine learning based fiber-induced nonlinearity compensation in energy-efficient coherent optical networks

Elias Giacoumidis,
Yi Lin,
Michaela Blott,
Liam P. Barry

Affiliations

Elias Giacoumidis: Radio and Optical Communications Lab, School of Electronic Engineering, Dublin City University, Glasnevin 9, Dublin, Ireland
Yi Lin: Radio and Optical Communications Lab, School of Electronic Engineering, Dublin City University, Glasnevin 9, Dublin, Ireland
Michaela Blott: Xilinx, Inc., 2020 Bianconi Ave., Citywest Business Campus, Dublin D24 T683, Ireland
Liam P. Barry: Radio and Optical Communications Lab, School of Electronic Engineering, Dublin City University, Glasnevin 9, Dublin, Ireland

DOI: https://doi.org/10.1063/1.5140609
Journal volume & issue: Vol. 5, no. 4
pp. 041301 – 041301-5

Abstract

Read online

We experimentally demonstrate the world’s 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.

Published in APL Photonics

ISSN: 2378-0967 (Online)
Publisher: AIP Publishing LLC
Country of publisher: United States
LCC subjects: Technology: Engineering (General). Civil engineering (General): Applied optics. Photonics
Website: https://aplphotonics.aip.org

About the journal