Predicting software anomalies using machine learning techniques
Document typeConference report
PublisherIEEE Computer Society Publications
Rights accessOpen Access
In this paper, we present a detailed evaluation of a set of well-known Machine Learning classifiers in front of dynamic and non-deterministic software anomalies. The system state prediction is based on monitoring system metrics. This allows software proactive rejuvenation to be triggered automatically. Random Forest approach achieves validation errors less than 1% in comparison to the well-known ML algorithms under avaluation. In order to reduce automatically the number of monitored parameters, needed to predict software anomalies, we analyze Lasso Regularization technique jointly with the Machine Learning classifiers to evaluate how the prediction accuracy could be guaranteed within an acceptable threshold. This allows to reduce drastically (around 60% in the best case) the number of monitoring parameters. The framework, based on ML and Lasso regularization techniques, has been validated using an e-commerce environment with Apache Tomcat server, and MySql database server.
CitationAlonso, J.; Belanche, Ll.; Avresky, D. Predicting software anomalies using machine learning techniques. A: IEEE International Symposium on Network Computing and Applications. "2011 IEEE International symposium on network computing and applications, NCA 2011: 25-27 August 2011, Cambridge, Massachusetts, US: proceedings". IEEE Computer Society Publications, 2011, p. 163-170.