论文信息 - An equalization method based on KNN for GPON with PAM4

An equalization method based on KNN for GPON with PAM4

A machine learning equalization technique based on KNN for 56Gpbs PAM4-GPONis proposed by nonlinear classification characteristics of KNN. Simulation results show that the proposed method can effectively optimizes the performance of equalization and increase bandwidth of the GPON network.

Xiangye Zeng | Jia Lu | Jianfei Liu | Jie Liu | Xujun Fan

[1] Jundong Liu,et al. Nonlinear Metric Learning for kNN and SVMs through Geometric Transformations , 2015, Neurocomputing.

[2] Weisheng Hu,et al. 56 Gbps IM/DD PON based on 10G-Class Optical Devices with 29 dB Loss Budget Enabled by Machine Learning , 2018, 2018 Optical Fiber Communications Conference and Exposition (OFC).

[3] Oskars Ozolins,et al. 100 GHz EML for High Speed Optical Interconnect Applications , 2016 .

[4] R. S Zhou,et al. A Review of a Text Classification Technique: K-Nearest Neighbor , 2015 .

[5] 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).

[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] Elias Giacoumidis,et al. 40 Gb/s/λ optical amplified PAM-4 PON with transmission over 30 km SMF using 10-G optics and simple DSP , 2017, 2017 Optical Fiber Communications Conference and Exhibition (OFC).

[8] 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).