Trade-Offs in Implementing Unsupervised Anomaly Detection with TAPI-Based Streaming Telemetry
Paper in proceeding, 2024
It is essential to be able to identify hidden anomalies in order to fully automate optical networks. This requires specific features from the application programming interfaces (APIs) used by the control plane and network monitoring solution. One of the solutions, Transport API (TAPI), utilizes advanced techniques in telemetry streaming. The update policy in TAPI enables key performance indicators (KPIs) to be transmitted only when changes are detected. In this paper, we explore how the update policy configuration of TAPI and the use of unsupervised learning (UL) interact in detecting previously unseen anomalies. Results reveal various trade-offs that network operators need to consider, including compute and time overhead, as well as the overall accuracy of UL.
Unsupervised learning
Optical networks
Machine Learning
Author
Piotr Lechowicz
Chalmers, Electrical Engineering, Communication, Antennas and Optical Networks
Carlos Natalino Da Silva
Chalmers, Electrical Engineering, Communication, Antennas and Optical Networks
Vignesh Karunakaran
Adtran Networks Se
Technische Universität Chemnitz
Achim Autenrieth
Adtran Networks Se
Thomas Bauschert
Technische Universität Chemnitz
Paolo Monti
Chalmers, Electrical Engineering, Communication, Antennas and Optical Networks
IEEE International Conference on High Performance Switching and Routing, HPSR
23255595 (ISSN) 23255609 (eISSN)
13-189798350363852 (ISBN)
25th IEEE International Conference on High Performance Switching and Routing, HPSR 2024
Pisa, Italy,
Pisa, Italy,
Subject Categories
Ecology
Bioinformatics (Computational Biology)
Computer Science
Computer Systems
DOI
10.1109/HPSR62440.2024.10635922