Machine learning-based EDFA Gain Model Generalizable to Multiple Physical Devices

Francesco Da Ros; Uiara Celine De Moura; Metodi P. Yankov

doi:10.1109/ECOC48923.2020.9333297

Machine learning-based EDFA Gain Model Generalizable to Multiple Physical Devices

Francesco Da Ros, Uiara Celine De Moura, Metodi P. Yankov

Centre of Excellence for Silicon Photonics for Optical Communications

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

Abstract

We report a neural-network based erbium-doped fiber amplifier (EDFA) gain model built from experimental measurements. The model shows low gain-prediction error for both the same device used for training (MSE leq 0.04 dB^2) and different physical units of the same make (generalization MSEleq 0.06 dB^2).

Original language	English
Title of host publication	Proceedings of 2020 European Conference on Optical Communications
Number of pages	4
Publisher	IEEE
Publication date	Dec 2020
Article number	9333297
ISBN (Electronic)	9781728173610
DOIs	https://doi.org/10.1109/ECOC48923.2020.9333297
Publication status	Published - Dec 2020
Event	46^th European Conference on Optical Communication - Virtual event, Brussels, Belgium Duration: 6 Dec 2020 → 10 Dec 2020 Conference number: 46 https://ecoco2020.org/

Conference

Conference	46^th European Conference on Optical Communication
Number	46
Location	Virtual event
Country/Territory	Belgium
City	Brussels
Period	06/12/2020 → 10/12/2020
Internet address	https://ecoco2020.org/

Bibliographical note

Funding Information:
This work is supported by the Villum Foundations (VYI grant OPTIC-AI no.29344), the EU H2020 programme (Marie Skłodowska-Curie grant no. 754462) and the DNRF CoE SPOC (ref. DNRF123).

Publisher Copyright:
© 2020 IEEE.

Access to Document

10.1109/ECOC48923.2020.9333297

OpenUrl availability

Full text

Cite this

@inproceedings{1c21165652344d01bbc1e04a82659ab3,

title = "Machine learning-based EDFA Gain Model Generalizable to Multiple Physical Devices",

abstract = "We report a neural-network based erbium-doped fiber amplifier (EDFA) gain model built from experimental measurements. The model shows low gain-prediction error for both the same device used for training (MSE leq 0.04 dB^2) and different physical units of the same make (generalization MSEleq 0.06 dB^2).",

author = "{Da Ros}, Francesco and {De Moura}, {Uiara Celine} and Yankov, {Metodi P.}",

note = "Funding Information: This work is supported by the Villum Foundations (VYI grant OPTIC-AI no.29344), the EU H2020 programme (Marie Sk{\l}odowska-Curie grant no. 754462) and the DNRF CoE SPOC (ref. DNRF123). Publisher Copyright: {\textcopyright} 2020 IEEE.; 46<sup>th</sup> European Conference on Optical Communication, ECOC 2020 ; Conference date: 06-12-2020 Through 10-12-2020",

year = "2020",

month = dec,

doi = "10.1109/ECOC48923.2020.9333297",

language = "English",

booktitle = "Proceedings of 2020 European Conference on Optical Communications",

publisher = "IEEE",

address = "United States",

url = "https://ecoco2020.org/",

}

TY - GEN

T1 - Machine learning-based EDFA Gain Model Generalizable to Multiple Physical Devices

AU - Da Ros, Francesco

AU - De Moura, Uiara Celine

AU - Yankov, Metodi P.

N1 - Conference code: 46

PY - 2020/12

Y1 - 2020/12

N2 - We report a neural-network based erbium-doped fiber amplifier (EDFA) gain model built from experimental measurements. The model shows low gain-prediction error for both the same device used for training (MSE leq 0.04 dB^2) and different physical units of the same make (generalization MSEleq 0.06 dB^2).

AB - We report a neural-network based erbium-doped fiber amplifier (EDFA) gain model built from experimental measurements. The model shows low gain-prediction error for both the same device used for training (MSE leq 0.04 dB^2) and different physical units of the same make (generalization MSEleq 0.06 dB^2).

U2 - 10.1109/ECOC48923.2020.9333297

DO - 10.1109/ECOC48923.2020.9333297

M3 - Article in proceedings

AN - SCOPUS:85098374679

BT - Proceedings of 2020 European Conference on Optical Communications

PB - IEEE

T2 - 46<sup>th</sup> European Conference on Optical Communication

Y2 - 6 December 2020 through 10 December 2020

ER -

Machine learning-based EDFA Gain Model Generalizable to Multiple Physical Devices

Abstract

Conference

Bibliographical note

Access to Document

OpenUrl availability

Fingerprint

Cite this