Supply-Power-Constrained Cable Capacity Maximization Using Deep Neural Networks
Junho Cho, Sethumadhavan Chandrasekhar, Erixhen Sula, Samuel Olsson, Ellsworth Burrows, Greg Raybon, Roland Ryf, Nicolas Fontaine, Jean-Christophe Antona, Steve Grubb, Peter Winzer, Andrew Chraplyvy
arXiv:1910.02050v11 citations
Originality Synthesis-oriented
AI Analysis
This work addresses power efficiency in fiber optic communication systems, which is incremental as it applies existing machine learning methods to a specific domain.
The paper tackled the problem of maximizing cable capacity under supply-power constraints in fiber optic networks by eliminating gain flattening filters and optimizing launch powers using deep neural networks, achieving a 19% capacity gain per Watt in a 12-span link.
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.