Title :
Training of neural networks to perform optical performance monitoring of a combination of accumulated signal nonlinearity, CD, PMD, and OSNR
Author :
Wu, Xiaoxia ; Jargon, Jeffrey ; Christen, Louis ; Willner, Alan
Author_Institution :
Dept. of Electr. Eng. - Syst., Univ. of Southern California, Los Angeles, CA
Abstract :
We propose a technique using artificial neural networks to simultaneously identify fiber nonlinearity, OSNR, CD, and PMD from eye-diagram and eye-histogram parameters. A correlation coefficient of 0.97 is obtained for a set of testing data.
Keywords :
neural nets; nonlinear optics; optical fibre dispersion; optical fibre networks; optical fibre polarisation; optical fibre testing; telecommunication computing; CD; OSNR; PMD; accumulated signal nonlinearity; artificial neural networks training; chromatic dispersion; correlation coefficient; eye-diagram parameters; eye-histogram parameters; fiber nonlinearity identification; first-order polarization-mode-dispersion; high performance optical network monitoring; optical signal-to-noise-ratio; Artificial neural networks; Monitoring; Neural networks; Neurons; Optical computing; Optical fiber networks; Optical noise; Optical receivers; Optical scattering; Signal to noise ratio;
Conference_Titel :
IEEE Lasers and Electro-Optics Society, 2008. LEOS 2008. 21st Annual Meeting of the
Conference_Location :
Acapulco
Print_ISBN :
978-1-4244-1931-9
Electronic_ISBN :
978-1-4244-1932-6
DOI :
10.1109/LEOS.2008.4688732
