Blind Nonlinearity Compensation by Machine-Learning-Based Clustering for Coherent Optical OFDM

This paper proposes clipping technique and clustering based on genetic simulated annealing algorithm to compensate nonlinear impairments for optical 16QAM CO-OFDM transmission. With our proposed algorithm, the Q-factor can be improved by approximately 1.9dB.

[1]  Ziad A. El-Sahn,et al.  Reduced Complexity Nonlinearity Compensation via Principal Component Analysis and Deep Neural Networks , 2019, 2019 Optical Fiber Communications Conference and Exhibition (OFC).

[2]  Elias Giacoumidis,et al.  Volterra-Based Reconfigurable Nonlinear Equalizer for Coherent OFDM , 2014, IEEE Photonics Technology Letters.

[3]  Wanyi Gu,et al.  Analytical Evaluation of Practical DBP-Based Intra-Channel Nonlinearity Compensators , 2013, IEEE Photonics Technology Letters.

[4]  Chia-Chien Wei,et al.  Convolutional Neural Network based Nonlinear Classifier for 112-Gbps High Speed Optical Link , 2018, 2018 Optical Fiber Communications Conference and Exposition (OFC).

[5]  Min Zhang,et al.  Nonlinearity Mitigation Using a Machine Learning Detector Based on $k$ -Nearest Neighbors , 2016, IEEE Photonics Technology Letters.