English

Advanced Equalization in 112 Gb/s Upstream PON Using a Novel Fourier Convolution-based Network

Machine Learning 2024-05-07 v1

Abstract

We experimentally demonstrate a novel, low-complexity Fourier Convolution-based Network (FConvNet) based equalizer for 112 Gb/s upstream PAM4-PON. At a BER of 0.005, FConvNet enhances the receiver sensitivity by 2 and 1 dB compared to a 51-tap Sato equalizer and benchmark machine learning algorithms respectively.

Cite

@article{arxiv.2405.02609,
  title  = {Advanced Equalization in 112 Gb/s Upstream PON Using a Novel Fourier Convolution-based Network},
  author = {Chen Shao and Elias Giacoumidis and Patrick Matalla and Jialei Li and Shi Li and Sebastian Randel and Andre Richter and Michael Faerber and Tobias Kaefer},
  journal= {arXiv preprint arXiv:2405.02609},
  year   = {2024}
}

Comments

4 pages, 5 figures

R2 v1 2026-06-28T16:16:32.587Z