自相似流量生成算法研究

The Study of Algorithms Generating Self-similar Traffic

大规模汇聚流量的研究在当前的网络环境下起着越来越重要的作用,无论在改善网络性能还是在提高网络入侵的防御能力方面。在大流量的限制条件下,网络模拟成为研究网络的主要手段,准确生成网络流量变得重要。当前网络研究表明流量满足自相似特征,但目前还没有直接产生自相似流量的流量产生器。本文通过从多种自相似生成的数学手段入手,通过实验比较得出快速傅立叶变换方法性能最优,并在ns2中实现了自相似流量产生器。

The Study of large-scale integrating network traffic plays a very important role in both improving the performance and enhancing the ability against intrusion. Network simulation is the most useful way of studying network under the large-scale condition. So it is important to generate network traffic correctly. Recent network traffic studies demonstrate that network traffic is self-similar. But there is no simple tool for generating self-similar traffic. This paper compares several math methods generating s...