基于非平稳型流量队列模型的Internet流量测量研究  

Internet Traffic Measurement Based on Non-Stationary Traffic Train Model

作　　者：杨家海[1] 吴建平[1] C Liu 

机构地区：[1]清华大学信息网络工程研究中心,北京100084 [2]美国贝尔实验室

出　　处：《电子学报》2004年第5期727-730,共4页Acta Electronica Sinica

基　　金："8 63"计划项目 (No.2 0 0 3AA1 0 31 1 0 )

摘　　要：针对大规模细粒度网络流量测量的现实困难 ,本文引入一种非平稳型流量队列模型NTT ,直接对粗粒度的流量采样进行建模 .NTT模型是大量活跃的流量队列的迭加 ,每个队列内部的流量变化过程用分形高斯噪声过程FGN描述 ,队列的到达过程形成非同构的泊松过程 ,队列的生存周期服从指数分布 .对CERNET主干网的实际流量测量分析验证了NTT模型的有效性 ,证实了NTT模型可用于基于各种粒度的流量测量的网络行为研究 .In order to solve the practical problem in the fine time-scale traffic measurement of large-scale networks, such as Internet, the paper introduced a non-stationary traffic train (NTT) model, which aims to directly model the coarse time-scale traffic samples. NTT model is the superposition of a large number of active traffic train segments, each of which can be described with a fractional Gaussian noise process, while train arrivals form a non-homogeneous Poisson process and train durations are exponential. The application of NTT model in the actual measurement and analysis of CERNET backbone traffic verifies the validation and effectiveness of NTT model, which confirms that NTT model can be used in the study of network behavior based on various time-scale traffic measurements.

关 键 词：互联网 网络测量 网络流量 网络行为 非平稳流量队列模型NTT 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]