ANN-Based Optical Performance Monitoring of QPSK Signals Using Parameters Derived From Balanced-Detected Asynchronous Diagrams

We demonstrate a technique of using artificial neural networks trained with parameters derived from asynchronous diagrams for optical performance monitoring of quadrature phase-shift-keying (QPSK) data signals. We show that asynchronous diagrams generated from balanced detection give superior results compared to single-ended detection in a 100 Gb/s QPSK system. Experimental demonstration verifies the effectiveness of the proposed technique.