Pre-equalization scheme for visible light communications with trial-and-error learning
Optics Letters · 15.03.2024 · 49 (6) · 1636
DOI: 10.1364/ol.516235 ↗Kurz gefasst
Fachartikel in der Zeitschrift Optics Letters, online erschienen am 15.03.2024. Verfasst von Shupeng Li und 3 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 13 Literaturangaben. Gefördert von: South China University of Technology.
Abstract (Originalsprache)
In this Letter, we propose a novel, to the best of our knowledge, neural network pre-equalizer based on the trial-and-error (TE) mechanism for visible light communication. This approach, unlike indirect learning (IL) architecture, does not require an additional auxiliary post-equalizer. Instead, it allows the pre-equalizer to be trained directly from the transmitter side through continuous interaction with the actual system. In a 1.95-Gbps 64-QAM carrier-less amplitude phase (CAP) free space optical transmission platform, the proposed scheme demonstrates superior nonlinear approximation capabilities and noise resilience. Specifically, the TE-recurrent neural network (RNN)-based pre-equalizer exhibits signal-to-noise ratio (SNR) gains of 0.8 dB and 1.8 dB over the IL-RNN-based and IL-Volterra-based pre-equalizers, respectively. We believe this is the first application of trial-and-error learning for training pre-equalizer in visible light communications.
Förderung
- South China University of Technology
Zitieren
APA
Li, S., Zou, Y., Liu, F., & Song, J. (2024). Pre-equalization scheme for visible light communications with trial-and-error learning. Optics Letters, 49(6), 1636. https://doi.org/10.1364/ol.516235
Vancouver
Li S, Zou Y, Liu F, Song J. Pre-equalization scheme for visible light communications with trial-and-error learning. Optics Letters. 2024;49(6):1636. doi:10.1364/ol.516235
BibTeX
@article{Li2024,
author = {Li, Shupeng and Zou, Yi and Liu, Fangming and Song, Jian},
title = {Pre-equalization scheme for visible light communications with trial-and-error learning},
journal = {Optics Letters},
year = {2024},
volume = {49},
number = {6},
pages = {1636},
doi = {10.1364/ol.516235}
}
EUVIMED