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

Paurakh Paudyal; Shuangyi Yan; Dimitra Simeonidou

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 proceeding › Conference Contribution (Conference Proceeding)

113 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 language	English
Title of host publication	Asia Communications and Photonics Conference/International Conference on Information Photonics and Optical Communications 2020 (ACP/IPOC)
Publisher	Optical Society of America (OSA)
Pages	S4C.2
Publication status	Published - 26 Oct 2020

Keywords

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

Access to Document

Full-text PDF (author’s accepted manuscript)
This is the author accepted manuscript (AAM). The final published version (version of record) is available online via OSA Publishing at https://www.osapublishing.org/conference.cfm?meetingid=144&yr=2020 . Please refer to any applicable terms of use of the publisher.
Accepted author manuscript, 457 KB

Handle.net

Persistent link

NDFIS2 National Dark Fibre Service
Simeonidou, D.
1/03/19 → 31/05/24
Project: Research

Cite this

@inproceedings{26440a56539046b99eb21025d70c2401,

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

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.",

keywords = "Erbium doped fiber amplifiers, Network topology, Neural networks, Optical networks, Optical signal to noise ratio, Stochastic gradient descent",

author = "Paurakh Paudyal and Shuangyi Yan and Dimitra Simeonidou",

year = "2020",

month = oct,

day = "26",

language = "English",

pages = "S4C.2",

booktitle = "Asia Communications and Photonics Conference/International Conference on Information Photonics and Optical Communications 2020 (ACP/IPOC)",

publisher = "Optical Society of America (OSA)",

address = "United States",

}

Toward Deployment of ML in Optical Networks, Transfer Learning, Monitoring and Modelling. / Paudyal, Paurakh; Yan, Shuangyi ; Simeonidou, Dimitra.

Asia Communications and Photonics Conference/International Conference on Information Photonics and Optical Communications 2020 (ACP/IPOC) . Optical Society of America (OSA), 2020. p. S4C.2.

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

TY - GEN

T1 - Toward Deployment of ML in Optical Networks, Transfer Learning, Monitoring and Modelling

AU - Paudyal, Paurakh

AU - Yan, Shuangyi

AU - Simeonidou, Dimitra

PY - 2020/10/26

Y1 - 2020/10/26

N2 - 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.

AB - 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.

KW - Erbium doped fiber amplifiers

KW - Network topology

KW - Neural networks

KW - Optical networks

KW - Optical signal to noise ratio

KW - Stochastic gradient descent

M3 - Conference Contribution (Conference Proceeding)

SP - S4C.2

BT - Asia Communications and Photonics Conference/International Conference on Information Photonics and Optical Communications 2020 (ACP/IPOC)

PB - Optical Society of America (OSA)

ER -

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

Abstract

Keywords

Access to Document

Handle.net

Fingerprint

Projects

NDFIS2 National Dark Fibre Service

Cite this