Autonomous fault detection in self-healing systems: comparing Hidden Markov Models and artificial neural networks

Christopher Schneider, Adam David Barker, Simon Andrew Dobson

Research output: Chapter in Book/Report/Conference proceedingConference contribution

6 Citations (Scopus)

Abstract

Autonomously detecting and recovering from faults is one approach for reducing the operational complexity and costs associated with managing computing environments. We present a novel methodology for autonomously generating investigation leads that help identify systems faults. Specifically, when historical feature data is present, Hidden Markov Models can be used to heuristically identify the root cause of a fault in an unsupervised manner. This approach improves
the state of the art by allowing self-healing systems to detect faults with greater autonomy than existing methodologies, and thus further reduce operational costs.
Original languageEnglish
Title of host publicationADAPT '14 The 4th International Workshop on Adaptive Self-tuning Computing Systems
Place of PublicationNew York, NY
PublisherACM
Pages24-31
ISBN (Print)9781450325141
DOIs
Publication statusPublished - 22 Jan 2014
Event4th International Workshop on Adaptive Self-tuning Computing Systems - Vienna Marriott Hotel, Ballroom B, Vienna, Australia
Duration: 22 Jan 201422 Jan 2014

Workshop

Workshop4th International Workshop on Adaptive Self-tuning Computing Systems
Country/TerritoryAustralia
CityVienna
Period22/01/1422/01/14

Keywords

  • Self-healing systems
  • Fault detection
  • Machine learning
  • Autonomic computing
  • Artificial neural networks
  • Hidden Markov Models

Fingerprint

Dive into the research topics of 'Autonomous fault detection in self-healing systems: comparing Hidden Markov Models and artificial neural networks'. Together they form a unique fingerprint.

Cite this