Intrusion detection system ean make effective alarm for illegality of networkusers, which is absolutely necessarily and important to build security environment of communicationbase service According to the principle t...Intrusion detection system ean make effective alarm for illegality of networkusers, which is absolutely necessarily and important to build security environment of communicationbase service According to the principle that the number of network traffic can affect the degree ofself-similar traffic, the paper investigates the variety of self-similarity resulted fromunconventional network traffic. A network traffic model based on normal behaviors of user isproposed and the Hursl parameter of this model can be calculated. By comparing the Hurst parameterof normal traffic and the self-similar parameter, we ean judge whether the network is normal or notand alarm in time.展开更多
Modeling of network traffic is a fundamental building block of computer science. Measurements of network traffic demonstrate that self-similarity is one of the basic properties of the network traffic possess at large ...Modeling of network traffic is a fundamental building block of computer science. Measurements of network traffic demonstrate that self-similarity is one of the basic properties of the network traffic possess at large time-scale. This paper investigates the change of non-stationary self-similarity of network traffic over time,and proposes a method of combining the discrete wavelet transform (DWT) and Schwarz information criterion (SIC) to detect change points of self-similarity in network traffic. The traffic is segmented into pieces around changing points with homogenous characteristics for the Hurst parameter,named local Hurst parameter,and then each piece of network traffic is modeled using fractional Gaussian noise (FGN) model with the local Hurst parameter. The presented experimental performance on data set from the Internet Traffic Archive (ITA) demonstrates that the method is more accurate in describing the non-stationary self-similarity of network traffic.展开更多
为了解决自相似模型难以进行自相似网络流量趋势预测的问题,提出时间序列分析中短时相关模型(自适应自回归模型)的方法用于流量数据的估计;同时为了提高预测精度,提出改进的最小平方格型(modified least squarelattice,MLSL)算法,使模...为了解决自相似模型难以进行自相似网络流量趋势预测的问题,提出时间序列分析中短时相关模型(自适应自回归模型)的方法用于流量数据的估计;同时为了提高预测精度,提出改进的最小平方格型(modified least squarelattice,MLSL)算法,使模型参数不断递推修正,收敛到最佳值。仿真试验结果验证了短时相关模型在网络流量预测应用中的可行性,实现了自相似网络流量的短期预测,该算法比最小平方(least square,LS)算法均方误差减少20%,具有收敛快、预测精度高的优点,而该算法的计算量减少一半。展开更多
文摘Intrusion detection system ean make effective alarm for illegality of networkusers, which is absolutely necessarily and important to build security environment of communicationbase service According to the principle that the number of network traffic can affect the degree ofself-similar traffic, the paper investigates the variety of self-similarity resulted fromunconventional network traffic. A network traffic model based on normal behaviors of user isproposed and the Hursl parameter of this model can be calculated. By comparing the Hurst parameterof normal traffic and the self-similar parameter, we ean judge whether the network is normal or notand alarm in time.
基金the National High Technology Research and Development Program (863) of China(Nos. 2005AA145110 and 2006AA01Z436)the Natural Science Foundation of Shanghai of China(No. 05ZR14083)the Pudong New Area Technology Innovation Public Service Platform of China(No. PDPT2005-04)
文摘Modeling of network traffic is a fundamental building block of computer science. Measurements of network traffic demonstrate that self-similarity is one of the basic properties of the network traffic possess at large time-scale. This paper investigates the change of non-stationary self-similarity of network traffic over time,and proposes a method of combining the discrete wavelet transform (DWT) and Schwarz information criterion (SIC) to detect change points of self-similarity in network traffic. The traffic is segmented into pieces around changing points with homogenous characteristics for the Hurst parameter,named local Hurst parameter,and then each piece of network traffic is modeled using fractional Gaussian noise (FGN) model with the local Hurst parameter. The presented experimental performance on data set from the Internet Traffic Archive (ITA) demonstrates that the method is more accurate in describing the non-stationary self-similarity of network traffic.
文摘为了解决自相似模型难以进行自相似网络流量趋势预测的问题,提出时间序列分析中短时相关模型(自适应自回归模型)的方法用于流量数据的估计;同时为了提高预测精度,提出改进的最小平方格型(modified least squarelattice,MLSL)算法,使模型参数不断递推修正,收敛到最佳值。仿真试验结果验证了短时相关模型在网络流量预测应用中的可行性,实现了自相似网络流量的短期预测,该算法比最小平方(least square,LS)算法均方误差减少20%,具有收敛快、预测精度高的优点,而该算法的计算量减少一半。
