Fiber Nonlinearity Equalizer using MLP-ANN for Coherent Optical OFDM

We propose a novel artificial neural network nonlinearity equalizer based on multiple layers perceptron(MLP-ANN NLE) for16-quadrature amplitude modulation (16-QAM) coherent optical orthogonal frequency division multiplexing (CO-OFDM) system. The scheme is effective for compensating for the four-wave mixing effect among subcarriers. Compared with the situation of non-compensated nonlinearity, this proposed scheme can increase the Q factor by 1.4 dB and 0.6 dB at 600 km and 2000 km respectively and the transmission distance can be increased by 400 km. It also shows a strong robustness in nonlinearity compensation.