Abstract
Nonlinearities in SOA-based wavelength conversion are experimentally tackled using post-blind-compensation based on machine learning clustering for coherent 16/64-QAM signals. We show that K-means outperforms fuzzy-logic since it tackles more effectively non-circularly- symmetric Gaussian noise and nonlinearity.
© 2019 The Author(s)
PDF ArticleMore Like This
Shoudong Liu, Jie Zhang, Yajie Li, Yongli Zhao, Kai Wang, Xiaokun Yang, and Yi Sun
T4B.6 Asia Communications and Photonics Conference (ACP) 2019
E. Giacoumidis, I. Aldaya, J. L. Wei, C. Sanchez, H. Mrabet, and L. P. Barry
STh1C.5 CLEO: Science and Innovations (CLEO:S&I) 2018
Xingyu Lu, Mingming Zhao, Liang Qiao, and Nan Chi
M2K.1 Optical Fiber Communication Conference (OFC) 2018