sas 15(3): e3

Research Article

A Framework for System Event Classification and Prediction by Means of Machine Learning

Download1919 downloads
  • @ARTICLE{10.4108/icst.valuetools.2014.258197,
        author={Teerat Pitakrat and Jonas Grunert and Oliver Kabierschke and Fabian Keller and Andre van Hoorn},
        title={A Framework for System Event Classification and Prediction by Means of Machine Learning},
        journal={EAI Endorsed Transactions on Self-Adaptive Systems},
        volume={1},
        number={3},
        publisher={EAI},
        journal_a={SAS},
        year={2015},
        month={2},
        keywords={event classification, event prediction, machine learning, online failure prediction},
        doi={10.4108/icst.valuetools.2014.258197}
    }
    
  • Teerat Pitakrat
    Jonas Grunert
    Oliver Kabierschke
    Fabian Keller
    Andre van Hoorn
    Year: 2015
    A Framework for System Event Classification and Prediction by Means of Machine Learning
    SAS
    EAI
    DOI: 10.4108/icst.valuetools.2014.258197
Teerat Pitakrat1,*, Jonas Grunert1, Oliver Kabierschke1, Fabian Keller1, Andre van Hoorn1
  • 1: University of Stuttgart, Institute of Software Technology
*Contact email: pitakrat@informatik.uni-stuttgart.de

Abstract

During operation, software systems produce large amounts of log events, comprising notifications of different severity from various hardware and software components. These data include important information that helps to diagnose problems in the system, e.g., post-mortem root cause analysis. Manual processing of system logs after a problem occurred is a common practice. However, it is time-consuming and error-prone. Moreover, this way, problems are diagnosed after they occurred—even though the data may already include symptoms of upcoming problems. To address these challenges, we developed the SCAPE approach for automatic system event classification and prediction, employing machine learning techniques. This paper introduces SCAPE, including a brief description of the proof-of-concept implementation. SCAPE is part of our Hora framework for online failure prediction in component-based software systems. The experimental evaluation, using a publicly available supercomputer event log, demonstrates SCAPE’s high classification accuracy and first results on applying the prediction to a real world data set.