Applying time series analysis to performance logs

Contemporary computer systems provide mechanisms for monitoring various performance parameters (e.g. processor or memory usage,

disc or network transfers), which are collected and stored in performance logs. An important issue is to derive characteristic features describing normal or abnormal behavior of the systems. For this purpose we uses various schemes of analyzing time series. They have been adapted to the specificity of performance logs and verified

using data collected from real systems. The presented approach is useful in evaluating system dependability.