Differentiable Machine Learning-Based Modeling for Directly-Modulated Lasers

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Hernandez, Sergio, Jovanovic, Ognjen, Peucheret, Christophe, Da Ros, Francesco, Zibar, Darko
Natura: Preprint
Pubblicazione: 2023
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866913355331010560
author Hernandez, Sergio
Jovanovic, Ognjen
Peucheret, Christophe
Da Ros, Francesco
Zibar, Darko
author_facet Hernandez, Sergio
Jovanovic, Ognjen
Peucheret, Christophe
Da Ros, Francesco
Zibar, Darko
contents End-to-end learning has become a popular method for joint transmitter and receiver optimization in optical communication systems. Such approach may require a differentiable channel model, thus hindering the optimization of links based on directly modulated lasers (DMLs). This is due to the DML behavior in the large-signal regime, for which no analytical solution is available. In this paper, this problem is addressed by developing and comparing differentiable machine learning-based surrogate models. The models are quantitatively assessed in terms of root mean square error and training/testing time. Once the models are trained, the surrogates are then tested in a numerical equalization setup, resembling a practical end-to-end scenario. Based on the numerical investigation conducted, the convolutional attention transformer is shown to outperform the other models considered.
format Preprint
id arxiv_https___arxiv_org_abs_2309_15747
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Differentiable Machine Learning-Based Modeling for Directly-Modulated Lasers
Hernandez, Sergio
Jovanovic, Ognjen
Peucheret, Christophe
Da Ros, Francesco
Zibar, Darko
Signal Processing
Information Theory
End-to-end learning has become a popular method for joint transmitter and receiver optimization in optical communication systems. Such approach may require a differentiable channel model, thus hindering the optimization of links based on directly modulated lasers (DMLs). This is due to the DML behavior in the large-signal regime, for which no analytical solution is available. In this paper, this problem is addressed by developing and comparing differentiable machine learning-based surrogate models. The models are quantitatively assessed in terms of root mean square error and training/testing time. Once the models are trained, the surrogates are then tested in a numerical equalization setup, resembling a practical end-to-end scenario. Based on the numerical investigation conducted, the convolutional attention transformer is shown to outperform the other models considered.
title Differentiable Machine Learning-Based Modeling for Directly-Modulated Lasers
topic Signal Processing
Information Theory
url https://arxiv.org/abs/2309.15747