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

Pitakrat, Teerat, Grunert, Jonas, Kabierschke, Oliver, Keller, Fabian and van Hoorn, Andre (2014) A Framework for System Event Classification and Prediction by Means of Machine Learning [Paper] In: 8th International Conference on Performance Evaluation Methodologies and Tools (ValueTools 2014), December 9-11, 2014, Bratislava, Slovakia.

hora-paper-cameraready.pdf - Submitted Version

Download (438Kb) | Preview
VALUETOOLS2014-SCAPE-slides.pdf - Presentation

Download (1621Kb) | Preview


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.

Document Type: Conference or Workshop Item (Paper)
Additional Information: To appear
Keywords: event classification, event prediction, machine learning, online failure prediction
Research affiliation: Kiel University > Software Engineering
Projects: Kieker
Date Deposited: 11 Nov 2014 10:07
Last Modified: 11 Dec 2014 14:09
URI: http://eprints.uni-kiel.de/id/eprint/26005

Actions (login required)

View Item View Item

Document Downloads

More statistics for this item...