Optimization of Raman amplifiers using machine learning

U. C. de Moura; F. Da Ros; D. Zibar; A. M. Rosa Brusin; A. Carena

doi:10.1109/SUM48717.2021.9505708

Optimization of Raman amplifiers using machine learning

U. C. de Moura
, F. Da Ros
, D. Zibar
, A. M. Rosa Brusin
, A. Carena

Centre of Excellence for Silicon Photonics for Optical Communications

Polytechnic University of Turin

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

Abstract

It has been recently demonstrated that neural networks can learn the complex pump-signal relations in Raman amplifiers. Here we experimentally show how these neural network models are applied to provide highly-accurate Raman amplifier designs and flexible configuration for ultra-wideband optical communication systems.

Original language	English
Title of host publication	Proceedings of 2021 IEEE Photonics Society Summer Topicals Meeting Series
Number of pages	2
Publisher	IEEE
Publication date	2021
ISBN (Electronic)	978-1-6654-1600-9
DOIs	https://doi.org/10.1109/SUM48717.2021.9505708
Publication status	Published - 2021
Event	2021 IEEE Photonics Society Summer Topicals Meeting Series - Virtual Conference, Cabo San Lucas, Mexico Duration: 19 Jul 2021 → 21 Jul 2021

Conference

Conference	2021 IEEE Photonics Society Summer Topicals Meeting Series
Location	Virtual Conference
Country/Territory	Mexico
City	Cabo San Lucas
Period	19/07/2021 → 21/07/2021

Keywords

Optical communications
Machine learning
Inverse system design
Optimization

Access to Document

10.1109/SUM48717.2021.9505708

OpenUrl availability

Check availability in DTU Findit

Cite this

@inproceedings{a4813a7034e2415caf8b848c2b597aa4,

title = "Optimization of Raman amplifiers using machine learning",

abstract = "It has been recently demonstrated that neural networks can learn the complex pump-signal relations in Raman amplifiers. Here we experimentally show how these neural network models are applied to provide highly-accurate Raman amplifier designs and flexible configuration for ultra-wideband optical communication systems.",

keywords = "Optical communications, Machine learning, Inverse system design, Optimization",

author = "\{de Moura\}, \{U. C.\} and \{Da Ros\}, F. and D. Zibar and \{Rosa Brusin\}, \{A. M.\} and A. Carena",

year = "2021",

doi = "10.1109/SUM48717.2021.9505708",

language = "English",

booktitle = "Proceedings of 2021 IEEE Photonics Society Summer Topicals Meeting Series",

publisher = "IEEE",

address = "United States",

note = "2021 IEEE Photonics Society Summer Topicals Meeting Series, SUM 2021 ; Conference date: 19-07-2021 Through 21-07-2021",

}

TY - GEN

T1 - Optimization of Raman amplifiers using machine learning

AU - de Moura, U. C.

AU - Da Ros, F.

AU - Zibar, D.

AU - Rosa Brusin, A. M.

AU - Carena, A.

PY - 2021

Y1 - 2021

N2 - It has been recently demonstrated that neural networks can learn the complex pump-signal relations in Raman amplifiers. Here we experimentally show how these neural network models are applied to provide highly-accurate Raman amplifier designs and flexible configuration for ultra-wideband optical communication systems.

AB - It has been recently demonstrated that neural networks can learn the complex pump-signal relations in Raman amplifiers. Here we experimentally show how these neural network models are applied to provide highly-accurate Raman amplifier designs and flexible configuration for ultra-wideband optical communication systems.

KW - Optical communications

KW - Machine learning

KW - Inverse system design

KW - Optimization

U2 - 10.1109/SUM48717.2021.9505708

DO - 10.1109/SUM48717.2021.9505708

M3 - Article in proceedings

BT - Proceedings of 2021 IEEE Photonics Society Summer Topicals Meeting Series

PB - IEEE

T2 - 2021 IEEE Photonics Society Summer Topicals Meeting Series

Y2 - 19 July 2021 through 21 July 2021

ER -

Optimization of Raman amplifiers using machine learning

Abstract

Conference

Keywords

Access to Document

OpenUrl availability

Fingerprint

Cite this