Pareto分布在TELNET客户端流量建模中的应用

Application of Pareto Distribution in Modeling TELNET Originator Traffic

针对 Internet上一个常用协议—— TELNET协议 ,并依据 Tcplib提供的经验分布曲线分析了它的客户端数据包产生的时间间隔分布及其突发序列的特性 .分析得出 ,Pareto分布在很大时间范围内能较好地描述 TELNET的客户端流量特性 .阐述了 Pareto模型和自相似模型以及 M/G/∞模型的关系 ,给出了 Pareto分布在建立自相似网络流量模型中的应用 .分析表明 ,在描述网络流量时自相似模型要比泊松模型有效和精确得多 。

This paper analyzed the distribution of packet interarrivals of TELNET originator, according to the empirical distribution of the Tcplib, and it found that packet interarrivals of TELNET originator can be well modeled by Pareto distribution in large time scales. The characteristics of the burst series and the relationship between Pareto model and selfsimilar model and M/G/∞ model were analyzed. It should indicate that the selfsimilar model is much better than the Poisson model when to model the network traffic. This new model can be widely applied in network performance analysis and network performance simulation.