English

Supply-Power-Constrained Cable Capacity Maximization Using Deep Neural Networks

Signal Processing 2019-10-07 v1 Machine Learning Machine Learning

Abstract

We experimentally achieve a 19% capacity gain per Watt of electrical supply power in a 12-span link by eliminating gain flattening filters and optimizing launch powers using machine learning by deep neural networks in a massively parallel fiber context.

Keywords

Cite

@article{arxiv.1910.02050,
  title  = {Supply-Power-Constrained Cable Capacity Maximization Using Deep Neural Networks},
  author = {Junho Cho and Sethumadhavan Chandrasekhar and Erixhen Sula and Samuel Olsson and Ellsworth Burrows and Greg Raybon and Roland Ryf and Nicolas Fontaine and Jean-Christophe Antona and Steve Grubb and Peter Winzer and Andrew Chraplyvy},
  journal= {arXiv preprint arXiv:1910.02050},
  year   = {2019}
}
R2 v1 2026-06-23T11:34:51.085Z