Skip to main navigation Skip to search Skip to main content

An overview on machine learning-based solutions to improve lightpath QoT estimation

  • Orange Labs
  • Institut Polytechnique de Paris

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

Abstract

Estimating lightpath Quality of Transmission (QoT) is crucial in network design and service provisioning. Recent studies have turned to Machine Learning (ML) techniques to improve the accuracy of QoT estimation. We distinguish two categories of solutions: the first category aims to build ML-based QoT estimation models that outperform the analytical model while the second category uses ML algorithms to reduce uncertainties on parameters provided as input to analytical model. In this overview, we describe the solutions in each category and discuss their practical feasibility and added benefit for operational networks.

Original languageEnglish
Title of host publication2020 22nd International Conference on Transparent Optical Networks, ICTON 2020
PublisherIEEE Computer Society
ISBN (Electronic)9781728184234
DOIs
Publication statusPublished - 1 Jul 2020
Event22nd International Conference on Transparent Optical Networks, ICTON 2020 - Bari, Italy
Duration: 19 Jul 202023 Jul 2020

Publication series

NameInternational Conference on Transparent Optical Networks
Volume2020-July
ISSN (Electronic)2162-7339

Conference

Conference22nd International Conference on Transparent Optical Networks, ICTON 2020
Country/TerritoryItaly
CityBari
Period19/07/2023/07/20

Keywords

  • Machine learning
  • QoT
  • WDM networks

Fingerprint

Dive into the research topics of 'An overview on machine learning-based solutions to improve lightpath QoT estimation'. Together they form a unique fingerprint.

Cite this