瞬时频率分析的网络流量异常检测  

Detection of Network Traffic Anomaly on Instantaneous Frequency Analysis

作　　者：张鹏[1] 胡光岷[1] 

机构地区：[1]电子科技大学宽带光纤传输与通信网技术教育部重点实验室,成都610054

出　　处：《电子科技大学学报》2007年第S2期1007-1010,共4页Journal of University of Electronic Science and Technology of China

基　　金：四川省青年基金(04ZQ026-028)

摘　　要：网络流量异常是指网络的流量行为偏离其正常行为的情形,准确、快速地检测网络流量的异常行为是保证网络有效运行的前提之一。现有的网络流量异常检测方法大都没有分析异常的频谱特性,因此它们都存在着不足之处。针对这些不足,利用异常流量和正常流量在频域特征量上的不同特点,提出了一种基于瞬时频率分析的方法检测网络流量异常。通过计算网络原始流量信号的瞬时频率,来突出反映流量的异常特性。同时针对滑动窗口的特点提出了一种计算瞬时频率的快速算法。仿真试验结果验证了该算法的有效性。Network traffic anomaly always takes place when the traffic action deviates from the normal action.Identifying network traffic anomalies accurately and rapidly is critical to the efficient operation of any network.The common detection methods of network traffic anomaly always have something wrong because they don't assay the anomaly's frequency characteristic.In this paper,a new algorithm is proposed based on instantaneous frequency analysis.The characteristic of traffic anomaly can be revealed more evidently through analyzing the instantaneous frequency of the original network flow data.And a fast instantaneous frequency algorithm is presented for the slip window.The experiment shows that the proposed algorithm can identify network traffic anomaly in time.

关 键 词：瞬时频率 网络流量异常检测 滑动窗口 方差分析 

分 类 号：TP393.08[自动化与计算机技术—计算机应用技术]