Learning from the optical spectrum: failure detection and identification [Invited]

Abstract

The availability of coarse-resolution cost-effective Optical Spectrum Analyzers (OSA) allows its widespread deployment in operators’ networks. In this paper, we explore several machine learning approaches for soft-failure detection, identification and localization that take advantage of OSAs. In particular, we present three different solutions for the two most common filter-related soft-failures; filter shift and tight filtering which noticeably deform the expected shape of the optical spectrum. However, filter cascading is a key challenge as it affects the shape of the optical spectrum similarly to tight filtering; the approaches are specifically designed to avoid the misclassification of properly operating signals when normal filter cascading effects are present. The proposed solutions are: $i) multi-classifier$ approach, which uses features extracted directly from the optical spectrum, $ii) single-classifier$ approach, which uses pre-processed features to compensate for filter cascading, and $iii) residual-based$ approach, which uses a residual signal computed from subtracting the acquired single by OSAs from an expected signal synthetically generated. Extensive numerical results are ultimately presented to compare the performance of the proposed approaches in terms of accuracy and robustness.