Generation And Research Of Self-similar Network Traffic

Through the research of LAN and WAN traffic, Leland and Klivansky found the self-similar nature of network traffic, but traditional network models can not describe this nature well. Self-similar is very important to system performance such as Cell Loss Ratio, network delay and so on, so study of self-similar models is increasingly significant nowadays.Firstly, we give the mathematic definition of self-similar process, give out its some characteristics on mathematic with physics and introduce how to examine the process if it is the self-similar process.We have a deep comparison to the exist LRD model. ON/OFF model has definite physical meanings, but its complexity is so large, RMD model runs fast, but it can not describe SRD well, FARIMA is a good traffic model that is capable of capturing both LRD and SRD behavior of a network traffic and is applied to the real network traffic data.It has an important means for aggregation and decomposition of self-similar process. so we do some analysis and simulation .We proves aggregation of self-similar process is still shows self-similar and the hurst parameter is the most large one.