Toward Deployment of ML in Optical Networks, Transfer Learning, Monitoring and Modelling

Paurakh Paudyal, Shuangyi Yan*, Dimitra Simeonidou

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference Contribution (Conference Proceeding)

2 Downloads (Pure)

Abstract

We present a novel approach for Quality of Transmission estimation using hybrid modelling and transfer-learning. Our method reduces the training data requirement by 80.27dB. The approach facilitates a streamlined ML life-cycle for data collection, training and deployment.
Original languageEnglish
Title of host publicationAsia Communications and Photonics Conference/International Conference on Information Photonics and Optical Communications 2020 (ACP/IPOC)
PublisherOptical Society of America (OSA)
PagesS4C.2
Publication statusPublished - 26 Oct 2020

Keywords

  • Erbium doped fiber amplifiers
  • Network topology
  • Neural networks
  • Optical networks
  • Optical signal to noise ratio
  • Stochastic gradient descent

Cite this