Advanced Equalization in 112 Gb/s Upstream PON Using a Novel Fourier Convolution-based Network

TL;DR

This paper introduces a novel Fourier Convolution-based Network equalizer for 112 Gb/s upstream PAM4-PON, significantly improving receiver sensitivity with low complexity, outperforming traditional and machine learning methods.

Contribution

The paper presents a new low-complexity equalizer based on Fourier convolution for high-speed PON, demonstrating superior performance over existing equalizers.

Findings

Enhances receiver sensitivity by 2 dB at BER 0.005

Outperforms 51-tap Sato equalizer and benchmark ML algorithms

Demonstrates effectiveness in experimental 112 Gb/s PAM4-PON setup

Abstract

We experimentally demonstrate a novel, low-complexity Fourier Convolution-based Network (FConvNet) based equalizer for 112 Gb/s upstream PAM4-PON. At a BER of 0.005, FConvNet enhances the receiver sensitivity by 2 and 1 dB compared to a 51-tap Sato equalizer and benchmark machine learning algorithms respectively.