English

A Novel Machine Learning-based Equalizer for a Downstream 100G PAM-4 PON

Signal Processing 2024-05-03 v1 Machine Learning

Abstract

A frequency-calibrated SCINet (FC-SCINet) equalizer is proposed for down-stream 100G PON with 28.7 dB path loss. At 5 km, FC-SCINet improves the BER by 88.87% compared to FFE and a 3-layer DNN with 10.57% lower complexity.

Keywords

Cite

@article{arxiv.2405.00720,
  title  = {A Novel Machine Learning-based Equalizer for a Downstream 100G PAM-4 PON},
  author = {Chen Shao and Elias Giacoumidis and Shi Li and Jialei Li and Michael Faerber and Tobias Kaefer and Andre Richter},
  journal= {arXiv preprint arXiv:2405.00720},
  year   = {2024}
}

Comments

3 pages, 6 figures, accepted by Optical Fiber Communications Conference and Exhibition 2024

R2 v1 2026-06-28T16:13:05.630Z