56 Gbps IM/DD PON based on 10G-Class Optical Devices with 29 dB Loss Budget Enabled by Machine Learning

We demonstrate 56Gbps PAM4 PON transmission over 25km SSMF using 10G-class DML and APD with 6 GHz 3-dB bandwidth. 29 dB loss budget is achieved by a novel equalization technique based on convolutional neural network.

[1]  Hanlin Feng,et al.  Demonstration of 50Gbps IM/DD PAM4 PON over 10GHz Class Optics Using Neural Network Based Nonlinear Equalization , 2017, 2017 European Conference on Optical Communication (ECOC).

[2]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[3]  Rafael Rios-Müller,et al.  Experimental estimation of optical nonlinear memory channel conditional distribution using deep neural networks , 2017, 2017 Optical Fiber Communications Conference and Exhibition (OFC).

[4]  Honglin Ji,et al.  First demonstration of symmetric 100G-PON in O-band with 10G-class optical devices enabled by dispersion-supported equalization , 2017, 2017 Optical Fiber Communications Conference and Exhibition (OFC).

[5]  Qi Yang,et al.  4×28 Gb/s PAM4 long-reach PON using low complexity nonlinear compensation , 2017, 2017 Optical Fiber Communications Conference and Exhibition (OFC).

[6]  Oskars Ozolins,et al.  High Speed PAM-8 Optical Interconnects with Digital Equalization Based on Neural Network , 2016, 2016 Asia Communications and Photonics Conference (ACP).

[7]  Demis Hassabis,et al.  Mastering the game of Go with deep neural networks and tree search , 2016, Nature.

[8]  Xiang Liu,et al.  50-Gb/s/λ TDM-PON based on 10G DML and 10G APD supporting PR10 link loss budget after 20-km downstream transmission in the O-band , 2017, 2017 Optical Fiber Communications Conference and Exhibition (OFC).