Optical performance monitoring of QPSK data channels by use of neural networks trained with parameters derived from asynchronous constellation diagrams

We demonstrate a technique for performance monitoring of quadrature phase-shift keying data channels by simultaneously identifying optical signal-to-noise ratio (OSNR), chromatic dispersion (CD), and polarization-mode dispersion (PMD) using neural networks trained with parameters derived from asynchronous constellation diagrams. A correlation coefficient of 0.987 is reported for a set of testing data from a 40 Gbps return-to-zero, quadrature phase-shift keying (RZ-QPSK) system. The root-mean-square (RMS) errors are 0.77 dB for OSNR, 18.71 ps/nm for CD, and 1.17 ps for DGD.