Applications of artificial neural networks in optical performance monitoring

Published

August 15, 2009

Author(s)

Jeffrey A. Jargon, Xiaoxia Wu, Ronald Skoog, Loukas Paraschis, Alan Willner

Abstract

Applications using artificial neural networks (ANNs) for optical performance monitoring (OPM) are proposed and demonstrated. Simultaneous identification of optical signal-to-noise-ratio (OSNR), chromatic dispersion (CD), and polarization-mode-dispersion (PMD) from eye-diagram parameters is shown via simulation in both 40 Gb/s on-off keying (OOK) and differential phase-shift-keying (DPSK) systems. Experimental verification is performed to simultaneously identify OSNR and CD. We then extend this technique to simultaneously identify accumulated fiber nonlinearity, OSNR, CD, and PMD from eye-diagram and eye-histogram parameters in a 3-channel 40 Gb/s DPSK wavelength- division multiplexing (WDM) system. Furthermore, we propose using this ANN approach to monitor impairment causing changes from a baseline. Simultaneous identification of accumulated fiber nonlinearity, OSNR, CD, and PMD causing changes from a baseline by use of the eye-diagram and eye-histogram parameters is obtained and high correlation coefficients are achieved with various baselines. Finally, the ANNs are also shown for simultaneous identification of in-phase/quadrature (I/Q) data misalignment and data/carver misalignment in return-to-zero differential quadrature phase shift keying (RZ-DQPSK) transmitters.

Citation

Journal of Lightwave Technology

Volume

27

Issue

16

Pub Type

Journals

Download Paper

Local Download

Keywords

neural networks, optical fiber communication, optical performance monitoring, phase modulation

Citation

Jargon, J. , Wu, X. , Skoog, R. , Paraschis, L. and Willner, A. (2009), Applications of artificial neural networks in optical performance monitoring, Journal of Lightwave Technology, [online], https://tsapps.nist.gov/publication/get_pdf.cfm?pub_id=901396 (Accessed January 18, 2025)