Premium
Multi‐scale anomaly detection for high‐speed network traffic
Author(s) -
Jiang Dingde,
Yao Cheng,
Xu Zhengzheng,
Qin Wenda
Publication year - 2015
Publication title -
transactions on emerging telecommunications technologies
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.366
H-Index - 47
ISSN - 2161-3915
DOI - 10.1002/ett.2619
Subject(s) - network traffic simulation , computer science , traffic generation model , anomaly detection , data mining , wavelet , network traffic control , anomaly (physics) , scale (ratio) , backbone network , real time computing , computer network , artificial intelligence , geography , cartography , physics , network packet , condensed matter physics
Abnormal network traffic has an important impact on network activities and leads to the severe damage to our networks because they are usually related with network faults and network attacks. How to detect effectively network traffic anomalies is an open issue for network researchers. This paper proposes a novel method for detecting traffic anomalies in high‐speed backbone networks, based on multi‐scale analysis. Firstly, the continuous wavelet transforms are performed for network traffic in multiple continuous scales. We then use the principal component analysis for the continuous wavelet transforms in the different scales and extract the nature of the anomalous network traffic. And the new mapping function is constructed to detect the abnormal traffic. Finally, we use the traffic data from the real network to validate our method. Simulation results show that our approach is more promising than the previous method.Copyright © 2013 John Wiley & Sons, Ltd.