Abstract
A novel nonlinear equalizer based on a multiple-input multiple-output (MIMO) deep neural network (DNN) is proposed and experimentally demonstrated for compensation of inter-subcarrier nonlinearities in a 40 Gb/s coherent optical orthogonal frequency division multiplexing system. Experimental results reveal that MIMO-DNN can extend the power margin by 4 dB at 2000 km of standard single-mode fiber transmission when compared to linear compensation or conventional single-input single-output DNN. It is also found that MIMO-DNN outperforms digital back propagation by increasing up to 1 dB the effective $Q$-factor and reducing by a factor of three the computational cost.
© 2020 Optical Society of America
Full Article | PDF ArticleMore Like This
Elias Giacoumidis, Sofien Mhatli, Tu Nguyen, Son T. Le, Ivan Aldaya, Mary E. McCarthy, Andrew D. Ellis, and Benjamin J. Eggleton
Opt. Lett. 41(11) 2509-2512 (2016)
Elias Giacoumidis, Son T. Le, Mohammad Ghanbarisabagh, Mary McCarthy, Ivan Aldaya, Sofien Mhatli, Mutsam A. Jarajreh, Paul A. Haigh, Nick J. Doran, Andrew D. Ellis, and Benjamin J. Eggleton
Opt. Lett. 40(21) 5113-5116 (2015)
Xinyu Chen, Hao Ming, Chenjia Li, Guangqiang He, and Fan Zhang
Opt. Lett. 46(7) 1700-1703 (2021)