Reservoir computing for equalization in a self-coherent receiver scheme

Short-reach optical networks, the backbone of data centers, face a significant challenge: transmitting high data rates at low cost and low energy consumption. While coherent signals can carry high data rates, coherent receivers are expensive and complex. Also, to equalize channel dispersion, they rely on digital signal processing modules, which consume large amounts of power and introduce more latency. Photonic reservoirs emerged as a way to process these signals in the analog optical domain, alleviating the power consumption and latency issues in state-of-the-art receivers. In this work, we show in simulations that a photonic reservoir combined with a self-coherent photonic receiver achieves a BER of 3.8 × 10<sup>-3</sup> for a 32 Gbaud 16-QAM signal and an 80 km link, requiring a low CSPR of 3 dB compared to state-of-the-art self-coherent receivers.

Authors

Publication Details

Journal
Optics Express
Published
2024-10-09
DOI
https://doi.org/10.1364/oe.534576
Citations
7
Primary Topic
Neural Networks and Reservoir Computing
Type
article
Field-Weighted Citation Impact
2.43

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Reservoir computing for equalization in a self-coherent receiver scheme

Aimen Zelaci, Peter Bienstman, Sarah Masaad
7 citations
Optics Express
Neural Networks and Reservoir Computing
2.43
article

Reservoir computing for equalization in a self-coherent receiver scheme

Aimen Zelaci, Peter Bienstman, Sarah Masaad
article en
7 citations

Abstract

Short-reach optical networks, the backbone of data centers, face a significant challenge: transmitting high data rates at low cost and low energy consumption. While coherent signals can carry high data rates, coherent receivers are expensive and complex. Also, to equalize channel dispersion, they rely on digital signal processing modules, which consume large amounts of power and introduce more latency. Photonic reservoirs emerged as a way to process these signals in the analog optical domain, alleviating the power consumption and latency issues in state-of-the-art receivers. In this work, we show in simulations that a photonic reservoir combined with a self-coherent photonic receiver achieves a BER of 3.8 × 10<sup>-3</sup> for a 32 Gbaud 16-QAM signal and an 80 km link, requiring a low CSPR of 3 dB compared to state-of-the-art self-coherent receivers.

Optics ExpressVol. 32(23)
Fonds Wetenschappelijk Onderzoek, Horizon 2020 Framework Programme
Climate action
Openalex Percentile: Top 9%
Neural Networks and Reservoir Computing
2.43
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.