Recurrent Neural Network (RNN) Based End-to-End Nonlinear Management for Symmetrical 50Gbps NRZ PON with 29dB+ Loss Budget

作者：Chenhui Ye, Dongxu Zhang, Xiaofeng Hu, Xiaoan Huang, Hanlin Feng, Kaibin Zhang · 年份：2018 · DOI：10.1109/ecoc.2018.8535428 · 被引用次数：39 · 研究领域：Optical Network Technologies、Advanced Photonic Communication Systems、Photonic and Optical Devices

We apply RNN as the end-to-end nonlinear equalization algorithms to enable symmetric 50Gb/s NRZ PON over 25G-optics with 29dB+ power budget when BER reaches 3.8E-3. Up to 60Gb/s-NRZ and 100Gb/s-PAM4 can be served for 20km in upstream and downstream, respectively.