The Self-Similarity Measurement for Internet Traffic based on Wavelet-analysis in G/G/1 Queueing System

• Main Authors: Shin-Tze Liu, 呂欣澤
• Other Authors: Yen-Chieh Ouyang
• Format: Others
• Language: en_US
• Online Access: http://ndltd.ncl.edu.tw/handle/02620869558175140796

碩士 === 國立中興大學 === 通訊工程研究所 === 97 === Network devices put packets on an internet link, and multiplex, or superimpose the packet form different active connections. Network arrivals are often modeled as Poisson processes for analytic simplicity, even thought a number of traffic studies have shown that packet inter-arrivals are not exponentially distribution. The notion of self-similarity has been shown to apply to wide-area and local-area network traffic. In recent years, many researchers reexamine the Poisson distribution model for traffic assumption and they point out that once the connection load is sufficiently large, the network begins pushing back on the attraction to Poisson and independence by causing queueing on the link-input router. Therefore, performance analysis of queueing system in long-range dependence traffic is needed to design a reliable network under the tremendous growth of internet traffic. In this thesis, we use a synthesize inter-arrival time distribution form ARIMA model and measure the sensitivity of output performance under various degrees of long-range dependent packet arrival. Experimental results show that packet arrival processes appear better modeled as self-similar processes.