Abstract
A novel scheme to mitigate fiber nonlinearity based on geometric constellation shaping via end-to-end auto-encoder learning and KNN deciding is investigated. Simulation results show that the scheme could effectively improve Q-factors under nonlinear situations.
© 2020 The Author(s)
PDF ArticleMore Like This
Vahid Aref and Mathieu Chagnon
W4I.3 Optical Fiber Communication Conference (OFC) 2022
Xiangyu Liu, Qi Zhang, Ran Gao, Xiangjun Xin, Xishuo Wang, Huan Chang, Bingchun Liu, Wenmao Zhou, Feng Tian, Qinghua Tian, and Zhipei Li
T3B.3 Asia Communications and Photonics Conference (ACP) 2021
Tobias Fehenberger, Helmut Griesser, and Jörg-Peter Elbers
Th1I.2 Optical Fiber Communication Conference (OFC) 2020