Feedforward Neural Network Enabled Optical Multi-Path Interference Mitigation for High-speed IMDD Transmission Systems

The performance of high-speed intensity modulation direct detection (IM-DD) transmission can be severely degraded by the Optical multipath interference (MPI) arising from multiple reflections mainly from polluted fiber connectors. In this paper, we propose a data-driven MPI mitigation scheme utilizing a feedforward neural network (FNN), and its performance is experimentally evaluated in a 28Gbaud PAM4 IMDD system with a transmission distance of 10.81km. Compared to other newly reported MPI mitigation schemes, our proposed approach achieves a 3dB improvement in signal-to-interference (SIR) tolerance at the KP4 BER threshold.