Low-Complexity FPGA-Accelerated NN-Based Adaptive Equalizer for 100 Gb/s IMDD PON

Research output: Chapter in Book/Report/Conference proceedingsConference proceedingpeer-review

Abstract

We demonstrate a low-complexity, field-programable gate array (FPGA)-based adaptive neural network equalizer to mitigate nonlinear impairments caused by semiconductor optical amplifier (SOA) gain saturation in a 100 Gb/s intensity modulation with direct detection (IMDD) passive optical network (PON). The proposed equalizer employs a 32-tap feedforward neural network (FFNN) for multi-symbol detection. This approach incorporates both offline training and adaptive learning techniques to ensure real-time adaptability. To enhance FPGA efficiency, the model is quantized to an 8-bit fixed-point format, and the FFNN core is parallelized to achieve a 100 Gb/s throughput. Experimental results show a dynamic range of 27.8 dB and a sensitivity of -22.8 dBm. This approach improves real-time digital signal processing and establishes a foundation for future machine learning-based solutions in next-generation PON systems, addressing key performance challenges.

Original languageEnglish
Title of host publication2025 IEEE International Conference on Machine Learning for Communication and Networking, ICMLCN 2025
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9798331520427
DOIs
Publication statusPublished - 2025
Event2nd IEEE International Conference on Machine Learning for Communication and Networking, ICMLCN 2025 - Barcelona, Spain
Duration: 26 May 202529 May 2025

Publication series

Name2025 IEEE International Conference on Machine Learning for Communication and Networking, ICMLCN 2025

Conference

Conference2nd IEEE International Conference on Machine Learning for Communication and Networking, ICMLCN 2025
Country/TerritorySpain
CityBarcelona
Period26/05/2529/05/25

Keywords

  • equalizer
  • FPGA
  • neural network
  • passive optical network

Fingerprint

Dive into the research topics of 'Low-Complexity FPGA-Accelerated NN-Based Adaptive Equalizer for 100 Gb/s IMDD PON'. Together they form a unique fingerprint.

Cite this