Abstract
We improve an inverse regular perturbation (RP) model using a machine learning (ML) technique. The proposed learned RP (LRP) model jointly optimizes step-size, gain and phase rotation for individual RP branches. We demonstrate that the proposed LRP can outperform the corresponding learned digital back-propagation (DBP) method based on a split-step Fourier method (SSFM), with up to 0.75 dB gain in a 800 km standard single mode fiber link. Our LRP also allows a fractional step-per-span (SPS) modeling to reduce complexity while maintaining superior performance over a 1-SPS SSFM-DBP.
© 2022 Optica Publishing Group
Full Article | PDF ArticleMore Like This
Xiatao Huang, Wenshan Jiang, Xingwen Yi, Jing Zhang, Taowei Jin, Qianwu Zhang, Bo Xu, and Kun Qiu
Opt. Express 30(20) 35526-35538 (2022)
Xiansong Fang, Xinyu Chen, Xiang Cai, Chuanchuan Yang, and Fan Zhang
Opt. Lett. 48(15) 4093-4096 (2023)
Takashi Inoue, Ryosuke Matsumoto, and Shu Namiki
Opt. Express 30(9) 14851-14872 (2022)