ML approaches for OTDR diagnoses in passive optical networks—event detection and classification: ways for ODN branch assignment
Michael Straub, Johannes Reber, Tarek Saier, Robert Borkowski, Shi Li, Dmitry Khomchenko, André Richter, Michael Färber, Tobias Käfer, R. Bonk
Abstract
An ML-supported diagnostics concept is introduced and demonstrated to detect and classify events on OTDR traces for application on a PON optical distribution network. We can also associate events with ODN branches by using deployment data of the PON. We analyze an ensemble classifier and neural networks, the usage of synthetic OTDR-like traces, and measured data for training. In our proof-of-concept, we show a precision of 98% and recall of 95% using an ensemble classifier on measured OTDR traces and a successful mapping to ODN branches or groups of branches. For emulated data, we achieve an average precision of 70% and an average recall of 91%.