XPM compensation in optical fiber transmission systems using neural-network-based digital signal processing

Shotaro Owaki; Moriya Nakamura

doi:10.1587/comex.2017XBL0149

This article has now been updated. Please use the final version.

XPM compensation in optical fiber transmission systems using neural-network-based digital signal processing

Shotaro Owaki, Moriya Nakamura

Author information

Keywords: Digital signal processing, Nonlinear distortion, XPM, Neural Network

JOURNAL FREE ACCESS Advance online publication

Article ID: 2017XBL0149

DOI https://doi.org/10.1587/comex.2017XBL0149

The final version of this article is now available: Vol. 7 (2018), No. 1 pp. 31-36

Details

Abstract

We propose a novel XPM compensation scheme using neural-network-based digital signal processing. A 16QAM signal distorted by XPM in optical fiber transmission system was successfully compensated for with the scheme simpler than digital back propagation (DBP). BER and EVM performance was investigated by numerical simulations, and the EVM was improved by more than 40% by the compensation.

Corresponding author

Register with J-STAGE for free!