A Machine Learning Approach for Dynamic Optical Channel Add/Drop Strategies that Minimize EDFA Power Excursions
Conference: ECOC 2016 - 42nd European Conference on Optical Communication
09/18/2016 - 09/22/2016 at Düsseldorf, Deutschland
Proceedings: ECOC 2016
Pages: 3Language: englishTyp: PDF
Personal VDE Members are entitled to a 10% discount on this title
Authors:
Huang, Yishen; Gutterman, Craig L.; Zussman, Gil; Samadi, Payman; Bergman, Keren (Department of Electrical Engineering, Columbia University, New York, NY 10027, USA)
Samoud, Wiem (Department of Electrical Engineering, Columbia University, New York, NY 10027, USA & LTCI, CNRS, Telecom Paris Saclay, Paris 75013, France)
Ware, Cedric (LTCI, CNRS, Télécom Paris Saclay, Paris 75013, France)
Lourdiane, Mounia (Télécom SudParis, Université Paris Saclay, Evry 91011, France)
Abstract:
We demonstrate a machine learning approach to characterize channel dependence of power excursions in mulit-span EDFA networks. This technique can determine accurate recommendations for channel add/drop with minimal excursions and is applicate to different network design.