Experimental demonstration of arbitrary Raman gain-profile designs using  machine learning

Uiara C. de Moura; Francesco Da Ros; A. Margareth Rosa Brusin; Andrea Carena; Darko Zibar

doi:10.1364/OFC.2020.T4B.2

Experimental demonstration of arbitrary Raman gain-profile designs using machine learning

Uiara C. de Moura^*
, Francesco Da Ros
, A. Margareth Rosa Brusin
, Andrea Carena
, Darko Zibar

^*Corresponding author for this work

Polytechnic University of Turin

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

231 Downloads (Orbit)

Abstract

A machine learning framework for Raman amplifier design is experimentally tested. Performance in terms of maximum error over the gain profile is investigated for various fiber types and lengths, demonstrating highly-accurate designs.

Original language	English
Title of host publication	Optical Fiber Communication Conference 2020
Number of pages	3
Publisher	IEEE
Publication date	2020
Article number	T4B.2
ISBN (Print)	978-1-943580-71-2
DOIs	https://doi.org/10.1364/OFC.2020.T4B.2
Publication status	Published - 2020
Event	Optical Fiber Communication Conference 2020 - San Diego Convention Center, San Diego, United States Duration: 8 Mar 2020 → 12 Mar 2020

Conference

Conference	Optical Fiber Communication Conference 2020
Location	San Diego Convention Center
Country/Territory	United States
City	San Diego
Period	08/03/2020 → 12/03/2020
Sponsor	Acacia Communications Inc., AC Photonics, Inc., Alibaba Group, Ciena Corporation, Cisco Systems

Bibliographical note

From the session: Machine Learning for Fiber Amplifier and Sensors (T4B)

Access to Document

10.1364/OFC.2020.T4B.2

FulltextAccepted author manuscript, 229 KB

OpenUrl availability

Check availability in DTU Findit

Cite this

@inproceedings{8038e519bab840e681b1655675911f03,

title = "Experimental demonstration of arbitrary Raman gain-profile designs using machine learning",

abstract = "A machine learning framework for Raman amplifier design is experimentally tested. Performance in terms of maximum error over the gain profile is investigated for various fiber types and lengths, demonstrating highly-accurate designs.",

author = "\{de Moura\}, \{Uiara C.\} and \{Da Ros\}, Francesco and Brusin, \{A. Margareth Rosa\} and Andrea Carena and Darko Zibar",

note = "From the session: Machine Learning for Fiber Amplifier and Sensors (T4B); Optical Fiber Communication Conference 2020, OFC 2020 ; Conference date: 08-03-2020 Through 12-03-2020",

year = "2020",

doi = "10.1364/OFC.2020.T4B.2",

language = "English",

isbn = "978-1-943580-71-2",

booktitle = "Optical Fiber Communication Conference 2020",

publisher = "IEEE",

address = "United States",

}

TY - GEN

T1 - Experimental demonstration of arbitrary Raman gain-profile designs using machine learning

AU - de Moura, Uiara C.

AU - Da Ros, Francesco

AU - Brusin, A. Margareth Rosa

AU - Carena, Andrea

AU - Zibar, Darko

N1 - From the session: Machine Learning for Fiber Amplifier and Sensors (T4B)

PY - 2020

Y1 - 2020

N2 - A machine learning framework for Raman amplifier design is experimentally tested. Performance in terms of maximum error over the gain profile is investigated for various fiber types and lengths, demonstrating highly-accurate designs.

AB - A machine learning framework for Raman amplifier design is experimentally tested. Performance in terms of maximum error over the gain profile is investigated for various fiber types and lengths, demonstrating highly-accurate designs.

U2 - 10.1364/OFC.2020.T4B.2

DO - 10.1364/OFC.2020.T4B.2

M3 - Article in proceedings

SN - 978-1-943580-71-2

BT - Optical Fiber Communication Conference 2020

PB - IEEE

T2 - Optical Fiber Communication Conference 2020

Y2 - 8 March 2020 through 12 March 2020

ER -