Predicting critical problems from execution logs of a large-scale software system

A. Beszédes, Lajos Jeno Fülöp, T. Gyimóthy

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

1 Citation (Scopus)

Abstract

The possibility of automatically predicting runtime failures in large-scale distributed systems such as critical slowdown is highly desirable, since this way a significant amount of manual effort can be saved. Based on the analysis of execution logs, a large amount of information can be gained for the purpose of prediction. Existing approaches - which are often based on achievements in Complex Event Processing - rarely employ intelligent analyses such as machine learning for the prediction. Predictive Analytics on the other hand, deals with analyzing past data in order to predict future events. We have developed a framework for our industrial partner to predict critical failures in their large-scale telecommunication software system. The framework is based on some existing solutions but include novel techniques as well. In this work, we overview the methods and present initial experimental evaluation.

Original languageEnglish
Title of host publicationSPLST 2009 and NW-MODE 2009 - Proceedings of 11th Symposium on Programming Languages and Software Tools and 7th Nordic Workshop on Model Driven Software Engineering
EditorsJari Peltonen
PublisherTampere University of Technology, TUT Press
Pages19-30
Number of pages12
ISBN (Electronic)9789521522123
Publication statusPublished - Jan 1 2009
Event11th Symposium on Programming Languages and Software Tools and 7th Nordic Workshop on Model Driven Software Engineering, SPLST 2009 and NW-MODE 2009 - Tampere, Finland
Duration: Aug 26 2009Aug 28 2009

Publication series

NameSPLST 2009 and NW-MODE 2009 - Proceedings of 11th Symposium on Programming Languages and Software Tools and 7th Nordic Workshop on Model Driven Software Engineering

Conference

Conference11th Symposium on Programming Languages and Software Tools and 7th Nordic Workshop on Model Driven Software Engineering, SPLST 2009 and NW-MODE 2009
CountryFinland
CityTampere
Period8/26/098/28/09

    Fingerprint

Keywords

  • Complex Event Processing
  • Execution log processing
  • Machine learning
  • Predicting runtime failures
  • Predictive Analytics

ASJC Scopus subject areas

  • Computer Science Applications
  • Software

Cite this

Beszédes, A., Fülöp, L. J., & Gyimóthy, T. (2009). Predicting critical problems from execution logs of a large-scale software system. In J. Peltonen (Ed.), SPLST 2009 and NW-MODE 2009 - Proceedings of 11th Symposium on Programming Languages and Software Tools and 7th Nordic Workshop on Model Driven Software Engineering (pp. 19-30). (SPLST 2009 and NW-MODE 2009 - Proceedings of 11th Symposium on Programming Languages and Software Tools and 7th Nordic Workshop on Model Driven Software Engineering). Tampere University of Technology, TUT Press.