Back to search

Carleton University

Machine Learning Approaches For Predicting Link Failures In Production Networks

Abstract

dc:description.abstract

To proactively address the problem of identifying flapping links (links that go down multiple times a day), we used Machine Learning (ML) tools to study metrics reported from Internet Protocol (IP) and optical layers of a topology provided by a real network operator. We studied the relevance of optical metrics, the underlying temporal relations, and the topological relations that help forecast link failures using Interior Gateway Protocol (IGP) configuration changes as a proxy. We discovered that optical features such as optical maximum and minimum power or unavailable and errored seconds increased the performance by about 9 percentage points while temporal and spatial features improved performance by 8 and 7 percentage points respectively. Furthermore, we used time series and graph neural networks to show that the smallest look-back window required to get such performance was five days and that neighboring links up to two hops away could have relevant information.

Degree

thesis:*
Name thesis:degree_name
Master of Applied Science (M.App.Sc.)
Level thesis:degree_level
Master's
Discipline thesis:degree_discipline
Engineering, Electrical and Computer
Grantor dc:publisher
Carleton University
Year dc:date.issued
2023

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Wubete, Bruck

Subjects

dc:subject × 3

Rights

dc:rights
Statement dc:rights
  • Copyright © 2023 the author(s). Theses may be used for non-commercial research, educational, or related academic purposes only. Such uses include personal study, distribution to students, research and scholarship. Theses may only be shared by linking to the Carleton University Institutional Repository and no part may be copied without proper attribution to the author; no part may be used for commercial purposes directly or indirectly via a for-profit platform; no adaptation or derivative works are permitted without consent from the copyright owner.
Language dc:language.iso
en

Identifiers

dc:identifier.*

Chain of custody

source
Harvested from
Carleton University
Base URL
carleton.scholaris.ca/server/oai/request
Last updated
2026-11-19
Source record
OAI-PMH GetRecord
citation

Wubete, Bruck. Machine Learning Approaches For Predicting Link Failures In Production Networks. Master's thesis, Carleton University, 2023. https://hdl.handle.net/20.500.14718/41320