Adaptation of the residual signal for filter failure detection in scenarios with multiple filter types

Abstract

To monitor the optical spectra of outgoing links, Optical Spectrum Analyzers (OSA) can deployed in the optical nodes acquiring the optical spectra of outgoing links and analyzing optical signals to detect those soft-failures that affect the shape of the spectrum, like Filter Shift and Filter Tightening. In this paper, we rely on the residual-based approach spectra analysis that uses a set of residual signals calculated by subtracting the measured signal by the OSA from an expected version of the signal. In this paper, we assume a network scenario, where nodes with optical filters of different characteristics (e.g., 2nd, 3rd, and 4th order Gaussian) are installed. In this scenario, the possibility of generating complete data set for machine learning training purposes that include every combination of filter and failure is difficult to achieve. Instead, we propose an adaptation mechanism that transform the expected effects of every filter type thus, emulating single filter-type networks. Exhaustive experiments are carried out to show the performance of the proposed adaptation under filter failures.