Studies on Autonomous Distributed Traffic Control for Overlay Networks

点击翻译按钮获取中文摘要

In overlay networks consisting of underlying physical nodes and links, data files are transferred by overlay routing managed at application level. The end-to-end file transfer delay depends on both logical and physical topologies resulting from overlay routing. In this research, we focus on six types of four-terminal four-router physical networks, and investigate the impact of topology inconsistency on the file-transfer delay. The analysis model is based on a two-layer queueing network, taking into account both logical and physical topologies. The model is validated in comparison with ns-2 simulation. Numerical examples show that the end-to-end file-transfer delay is small when both logical and physical topologies are the same. It is also observed that the end-to-end delay significantly depends on the traffic intensity for some logical topologies, regardless of physical topology.Next, we consider Skype which has been receiving considerable attention as a peer-to-peer (P2P) Internet tel … More ephony application. In Skype, a voice connection is established via super nodes chosen from among ordinary end-user nodes. User information such as an IP address and port number of an online Skype node is managed by super nodes in a decentralized manner where the number of super nodes changes dynamically according to the number of online Skype nodes. Here, we analyze the performance of this decentralized management system of user information. In our analytical model, new nodes join the system according to a nonstationary Poisson process, and the online-node process associated with the number of super nodes is analyzed with a nonstationary Markov chain. We derive the system of difference-differential equations for the probability distribution of the number of online nodes to compute performance measures using the stationary peakedness approximation method. Numerical examples show that the user-information management system based on P2P can keep the quality of service (QoS) more stable than a client-server system with a centralized server of high performance. Less