Skip to main navigation Skip to search Skip to main content

A Causal Perturbation-Aided Temporal Neural Network Scheme for Nonlinear Signal Equalization in Coherent Optical Fiber Communication Systems

  • Xinyu Yuan
  • , Qi Zhang*
  • , Xiangjun Xin
  • , Ran Gao
  • , Xiaofang Hu
  • , Gang Fan
  • , Qihan Zhao
  • , Yi Zhao
  • , Zhiqi Huang
  • , Fu Wang
  • , Feng Tian
  • , Yongjun Wang
  • , Qinghua Tian
  • *Corresponding author for this work
  • Beijing University of Posts and Telecommunications
  • State Key Lab. of Information Photonics and Optical Communication
  • Beijing Key Laboratory of Space-ground Interconnection and Convergence
  • Beijing Institute of Technology
  • Beijing Institute of Control and Electronics Technology

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

A causal perturbation-aided temporal neural network scheme is proposed to reduce input feature dimensionality and computational complexity while maintaining equalization performance, and is experimentally validated on a 5 × 216 Gb/s DP-64QAM Nyquist-WDM system.

Original languageEnglish
Title of host publication2025 23rd International Conference on Optical Communications and Networks, ICOCN 2025
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9798331548759
DOIs
Publication statusPublished - 2025
Event23rd International Conference on Optical Communications and Networks, ICOCN 2025 - Zhangjiajie, China
Duration: 28 Jul 202531 Jul 2025

Publication series

Name2025 23rd International Conference on Optical Communications and Networks, ICOCN 2025

Conference

Conference23rd International Conference on Optical Communications and Networks, ICOCN 2025
Country/TerritoryChina
CityZhangjiajie
Period28/07/2531/07/25

Keywords

  • Perturbation
  • WDM
  • coherent optical fiber communication systems
  • nonlinear equalization

Fingerprint

Dive into the research topics of 'A Causal Perturbation-Aided Temporal Neural Network Scheme for Nonlinear Signal Equalization in Coherent Optical Fiber Communication Systems'. Together they form a unique fingerprint.

Cite this