Quality of Transmission Prediction with Machine Learning for Dynamic Operation of Optical WDM Networks

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

We propose a cognitive scalable method based on neural networks to address dynamic and agile provisioning of optical physical layer without prior knowledge of network specifications. Experimental demonstrations on a mesh network achieve 90th percentile OSNR prediction of 0.25dB Root-Mean-Squared-Error.

Original languageEnglish
Title of host publication43rd European Conference on Optical Communication, ECOC 2017
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1-3
Number of pages3
ISBN (Electronic)9781538656242
DOIs
Publication statusPublished - 21 Sept 2017
Event43rd European Conference on Optical Communication, ECOC 2017 - Gothenburg, Sweden
Duration: 17 Sept 201721 Sept 2017

Publication series

NameEuropean Conference on Optical Communication, ECOC
Volume2017-September

Conference

Conference43rd European Conference on Optical Communication, ECOC 2017
Country/TerritorySweden
CityGothenburg
Period17/09/1721/09/17

Fingerprint

Dive into the research topics of 'Quality of Transmission Prediction with Machine Learning for Dynamic Operation of Optical WDM Networks'. Together they form a unique fingerprint.

Cite this