Using Wavelets for Compression and Detecting Events in Anomalous Network Traffic

Monitoring and measuring various metrics of high-data rate networks produces a vast amount of information over a long period of time making the storage of the monitored data a serious issue. Furthermore, for the collected monitoring data to be useful to network analysts, these measurements need to be processed in order to detect interesting characteristics.In this paper wavelet analysis is used as a multi-resolution analysis tool for compression of data rate measurements. Two known thresholds are suggested for lossy compression and event detection purposes. Results show high compression ratios while preserving the quality (quantitative and visual aspects) and the energy of the signal and detection of sudden changes are achievable.