Analysis and Modeling of Traffic from Residential High Speed Internet Subscribers

摘要

Recently we observe wide use of P2P(Peer to Peer) applications of which traffic shows different statistical characteristics compared with traditional applications such as web and FTP (File Transfer Protocol). In this paper, we measured traffic from a subscriber network of KT(Korea Telecom) to analyze P2P traffic characteristics. Analysis results show that P2P traffic is much burstier than web traffic and its upstream and downstream traffic is symmetric which is also very much different from that of conventional applications. To predict QoS related parameters such as packet drop probability and delay, we modeled P2P traffic using two self-similar traffic models and compare their accuracies. With simulation we show that the self-similar traffic models we derive predict the performance of P2P traffic accurately and thus when we design a network or evaluate its performance, we can use the P2P traffic model as reference input traffic.