Anomaly Detection by Diffusion Wavelet-Based Analysis on Traffic Matrix

Diffusion wavelets (DW) transform has been successfully used in Multi-Resolution Analysis (MRA) of traffic matrices because it inherently adaptsto the structure of the underlying network. But many applications based on DW analysis such as anomaly detection, routing optimization and capacity plan have not been well developed. The paper describes how two-dimensional version ofDW transform is used to analyze the traffic matrix and applied in anomaly detection. The analysis results demonstrate the efficiency of DW-based technique in anomaly detection in practical networks. It also shows that this new technique is potential to be used in many other network applications.