A Machine Learning Approach for Dynamic Optical Channel Add/Drop Strategies that Minimize EDFA Power Excursions
Konferenz: ECOC 2016 - 42nd European Conference on Optical Communication
18.09.2016 - 22.09.2016 in Düsseldorf, Deutschland
Tagungsband: ECOC 2016
Seiten: 3Sprache: EnglischTyp: PDF
Persönliche VDE-Mitglieder erhalten auf diesen Artikel 10% Rabatt
Autoren:
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)
Inhalt:
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.