Published March 6, 2022 | Version v1
Conference paper Open

Microservice-Based Unsupervised Anomaly Detection Loop for Optical Networks

Authors/Creators

  • 1. Chalmers University of Technology, Gothenburg
  • 2. Centro Tecnológico de Telecomunicaciones de Cataluña (CTTC)

Description

Unsupervised learning (UL) is a technique to detect previously unseen anomalies without needing labeled datasets. We propose the integration of a scalable UL-based inference component in the monitoring loop of an SDN-controlled optical network. © 2022 The Author(s)

Notes

Acknowledgements: Work partially supported by the EC H2020 TeraFlow (101015857), Spanish AURORAS (RTI2018-099178-I00) and Vetenskapsrådet (2019-05008). Upon publication, the source code of this work will be available at https://github.com/carlosnatalino/2022-OFC-unsupervised-learning.

Files

0000015953.pdf

Files (288.4 kB)

Name Size Download all
md5:07cb960ef369b8b6ade5a430f8ebca73
288.4 kB Preview Download

Additional details

Funding

European Commission
TeraFlow - Secured autonomic traffic management for a Tera of SDN flows 101015857