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%.

© 2024 Optica Publishing Group

Faulty branch identification in passive optical networks using machine learning

Khouloud Abdelli, Carsten Tropschug, Helmut Griesser, and Stephan Pachnicke
J. Opt. Commun. Netw. 15(4) 187-196 (2023)

Mitigation of the parallel-path effect for reliable monitoring of a passive optical network using standard optical time domain reflectometry

Patryk J. Urban
J. Opt. Commun. Netw. 15(10) 776-782 (2023)

AI/ML-as-a-Service for optical network automation: use cases and challenges [Invited]

Carlos Natalino, Ashkan Panahi, Nasser Mohammadiha, and Paolo Monti
J. Opt. Commun. Netw. 16(2) A169-A179 (2024)

Experimental investigation of machine-learning-based soft-failure management using the optical spectrum

Lars E. Kruse, Sebastian Kühl, Annika Dochhan, and Stephan Pachnicke
J. Opt. Commun. Netw. 16(2) 94-103 (2024)

Detection of Fiber Faults in Passive Optical Networks

P. J. Urban, A. Getaneh, J. P. von der Weid, G. P. Temporão, G. Vall-llosera, and J. Chen
J. Opt. Commun. Netw. 5(11) 1111-1121 (2013)