Machine Learning Enabled Directly Modulated Lasers

Sergio Hernandez; Christophe Peucheret; Francesco Da Ros; Darko Zibar

doi:10.1109/ICTON62926.2024.10648111

Machine Learning Enabled Directly Modulated Lasers

Sergio Hernandez, Christophe Peucheret, Francesco Da Ros, Darko Zibar

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

Abstract

The complex dynamics of systems based on directly modulated lasers (DMLs) can hinder their optimization, as their simulation entails numerical methods where gradient calculation is not readily available. Our proposed solution combines data-driven DML modeling with end-to-end (E2E) learning techniques to obtain optimal link configurations.

Original language	English
Title of host publication	Proceedings of 24^th International Conference on Transparent Optical Networks
Number of pages	1
Publisher	IEEE
Publication date	2024
ISBN (Print)	979-8-3503-7733-0
DOIs	https://doi.org/10.1109/ICTON62926.2024.10648111
Publication status	Published - 2024
Event	24^th International Conference on Transparent Optical Networks - Polytechnic University of Bari, Bari , Italy Duration: 14 Jul 2024 → 18 Jul 2024

Conference

Conference	24^th International Conference on Transparent Optical Networks
Location	Polytechnic University of Bari
Country/Territory	Italy
City	Bari
Period	14/07/2024 → 18/07/2024

Access to Document

10.1109/ICTON62926.2024.10648111

OpenUrl availability

Full text

Cite this

@inproceedings{372020199dc94b77aed151f40320a183,

title = "Machine Learning Enabled Directly Modulated Lasers",

abstract = "The complex dynamics of systems based on directly modulated lasers (DMLs) can hinder their optimization, as their simulation entails numerical methods where gradient calculation is not readily available. Our proposed solution combines data-driven DML modeling with end-to-end (E2E) learning techniques to obtain optimal link configurations.",

author = "Sergio Hernandez and Christophe Peucheret and Ros, {Francesco Da} and Darko Zibar",

year = "2024",

doi = "10.1109/ICTON62926.2024.10648111",

language = "English",

isbn = "979-8-3503-7733-0",

booktitle = "Proceedings of 24th International Conference on Transparent Optical Networks",

publisher = "IEEE",

address = "United States",

note = "24<sup>th</sup> International Conference on Transparent Optical Networks, ICTON 2024 ; Conference date: 14-07-2024 Through 18-07-2024",

}

TY - GEN

T1 - Machine Learning Enabled Directly Modulated Lasers

AU - Hernandez, Sergio

AU - Peucheret, Christophe

AU - Ros, Francesco Da

AU - Zibar, Darko

PY - 2024

Y1 - 2024

N2 - The complex dynamics of systems based on directly modulated lasers (DMLs) can hinder their optimization, as their simulation entails numerical methods where gradient calculation is not readily available. Our proposed solution combines data-driven DML modeling with end-to-end (E2E) learning techniques to obtain optimal link configurations.

AB - The complex dynamics of systems based on directly modulated lasers (DMLs) can hinder their optimization, as their simulation entails numerical methods where gradient calculation is not readily available. Our proposed solution combines data-driven DML modeling with end-to-end (E2E) learning techniques to obtain optimal link configurations.

U2 - 10.1109/ICTON62926.2024.10648111

DO - 10.1109/ICTON62926.2024.10648111

M3 - Article in proceedings

SN - 979-8-3503-7733-0

BT - Proceedings of 24th International Conference on Transparent Optical Networks

PB - IEEE

T2 - 24<sup>th</sup> International Conference on Transparent Optical Networks

Y2 - 14 July 2024 through 18 July 2024

ER -

Machine Learning Enabled Directly Modulated Lasers

Abstract

Conference

Access to Document

OpenUrl availability

Fingerprint

Cite this