Machine Learning-Driven Low-Complexity Optical Power Optimization for Point-to-Point Links (W2A.19)
Presenter: Isaia Andrenacci, Nokia Bell Labs
We propose a strategy to dynamically adjust transmitted power solely based on the analysis of performance fluctuations due to polarization-dependent loss. We show that our method converges faster to optimum compared to a standard approach.
Authors:Isaia Andrenacci, Nokia Bell Labs / Matteo Lonardi, Nokia Bell Labs / Petros Ramantanis, Nokia Bell Labs / Élie Awwad, Télécom Paris / Ekhiñe Irurozki, Télécom Paris / Stephan Clémençon, Télécom Paris / Paolo Serena, University of Parma / Chiara Lasagni, University of Parma / Sébastien Bigo, Nokia Bell Labs / Patricia Layec, Nokia Bell Labs