Network Traffic Deviation Detection Based on Fractal Dimension

Abstract

In this paper we examine aggregate network traffic for deviation detection. The precise and fast detection of network traffic deviation is crucial to improve the efficient operation of a network. It is often difficult to detect the time when the defects occur in a network. In this article, a new algorithm is bestowed to supervise the aggregate network traffic to fast detect the time deviation transpires in a network. This is performed by supervising the statistical attributes of the time series depicting the network conduct. The procedure examines the network conduct using fractal dimension and discrete stationary wavelet transform. In the suggested procedure, after implementing discrete stationary wavelet transform on the signal depicting the network traffic, the fractal dimension of the disintegrated signal is computed in a sliding window. Then, variations of signal fractal dimension are regarded for deviation detection. Performance of the suggested procedure is compared with that of three other existent procedures using artificial substance signal. The results show superiority of the suggested procedure in terms of preciseness compared to existent procedures.