Inproceedings4001

A Novel Machine Learning-based Equalizer for a Downstream 100G PAM-4 PON

Chen Shao, Elias Giacoumidis, Shi Li, Jialei Li, Michael Färber, Tobias Käfer, André Richter

Published: 2024

Buchtitel: Proceedings of the 2024 Optical Fiber Communication Conference and Exhibition (OFC'24)
Verlag: IEEE

Referierte Veröffentlichung

BibTeX

Kurzfassung
A frequency-calibrated SCINet (FC-SCINet) equalizer is proposed for downstream 100G PON with 28.7 dB path loss. At 5 km, FC-SCINet improves the BER by ~88.87% compared to FFE and a 3-layer DNN with 10.57% lower complexity.

Download: Media:SCINet_OFC2024.pdf

Projekt

KIGLIS

Forschungsgruppe

Web Science

Forschungsgebiet

Künstliche Intelligenz