重尾ON/OFF源模型生成自相似业务流研究

因为传统模型没有考虑网络业务流量各种时间尺度都具有突发性，因此是不完善的，一系列的测量结果表明，网络业务流量显示自相似性，重尾分布ON／OFF模型能比较好地解释自相似业务流的产生原因，可以把LAN上的业务分解为多个活动（active)主机对之间的业务流，本文通过系统的仿真实验研究了重尾ON／OFF源模型生成自相似流的机理，并与理论结果进行了对比，而且补充了理论结果。

Study of the Self-similar Traffic Stream Generated by Heavy-tailed ON/OFF Source Model

It is widely accepted that conventional models do not adequately model network traffic since they do not take into account its inherently bursty nature. A series of measurements have showed that network traffic is self-similar. The heavy-tailed ON/OFF Source model can make clear the reason why the network traffic is self-similar. It is possible to separate the aggregate LAN traffic into the individual components representing traffic flows between each active pairs of host computers. In this paper, we study mechanism of heavy-tailed ON/OFF source model producing self-similar traffic stream is studied by systematic simulations, and the simulation results are compared with theoretical results as to complement the latter.