Research on Auto-adaptive Traffic-Aware Abnormal Detection Method

Abnormal traffic detection is important to network management. This paper aims at the characteristic of multi-hop network, and defines abnormity that traffic-burst after failure. Then the paper presents a fast auto-adaptive traffic-aware abnormal detection method. This method compresses data via efficient histogram, and detects double-size bursts via congregate function. We analyze the status of links and node via being aware traffic and we can get status of network fast and accurately. The paper does experiment to validate the validity and advance in performance of this method which compares with other burst detection methods.