Optical performance monitoring using artificial neural networks trained with empirical moments of asynchronously sampled signal amplitudes

Faisal Nadeem Khan, Thomas Shun Rong Shen, Yudi Zhou, Pak Tao Lau, Chao Lu

Research output: Journal article publicationJournal articleAcademic researchpeer-review

68 Citations (Scopus)

Abstract

We propose a low-cost technique for simultaneous and independent optical signal-to-noise ratio (OSNR), chromatic dispersion (CD), and polarization-mode dispersion (PMD) monitoring in 40/56-Gb/s return-to-zero differential quadrature phase-shift keying (RZ-DQPSK) and 40-Gb/s RZ-DPSK systems, using artificial neural networks (ANN) trained with empirical moments of asynchronously sampled signal amplitudes. The proposed technique employs an extremely simple hardware and digital signal processing to enable multi-impairment monitoring at different data rates and for various modulation formats without necessitating hardware changes. Simulation results demonstrate wide dynamic ranges and good monitoring accuracies.
Original languageEnglish
Article number6168795
Pages (from-to)982-984
Number of pages3
JournalIEEE Photonics Technology Letters
Volume24
Issue number12
DOIs
Publication statusPublished - 22 May 2012

Keywords

  • Artificial neural networks
  • Asynchronous sampling
  • Empirical moments
  • Multi-impairment monitoring
  • Optical performance monitoring

ASJC Scopus subject areas

  • Electronic, Optical and Magnetic Materials
  • Atomic and Molecular Physics, and Optics
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'Optical performance monitoring using artificial neural networks trained with empirical moments of asynchronously sampled signal amplitudes'. Together they form a unique fingerprint.

Cite this