A Haar Transform-Based Detection Approach to Network Traffic Anomalies in Power Telecommunication Access Networks

This paper proposes a new detection approach to find the abnormal parts in network traffic. Firstly, network traffic is regarded as a discrete time series. Then it is normalized and is carried out the feature component decomposed. Secondly, according to mathematical theory, the feature components in network traffic is effectively refined from the normalized series. The network traffic is divided into feature and residual components. Thirdly, the Haar time-frequency decomposition is carried out for these two components. In this case, a quick anomaly detection algorithm is presented. Simulation results show that our approach is feasible.