A Novel Machine Learning-based Equalizer for a Downstream 100G PAM-4 PON
Chen Shao, Elias Giacoumidis, Shi Li, Jialei Li, Michael Faerber,, Tobias Kaefer, and Andre Richter
TL;DR
This paper introduces a new frequency-calibrated SCINet equalizer designed for 100G PAM-4 PON systems, significantly enhancing BER performance over long distances with reduced complexity.
Contribution
It presents a novel FC-SCINet equalizer that outperforms traditional methods in BER and complexity for 100G PON applications.
Findings
88.87% BER improvement at 5 km
Reduced complexity by 10.57% compared to DNN
Effective for 28.7 dB path loss
Abstract
A frequency-calibrated SCINet (FC-SCINet) equalizer is proposed for down-stream 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.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsOptical Network Technologies · Advanced Photonic Communication Systems · Photonic and Optical Devices