Modeling and performance analysis of internet, WLAN and WMAN

Abstract

Wireless mesh networks (WMNs) have emerged as a key technology for next-generation wireless networking. Because of their advantages over other wireless networks, WMNs are undergoing rapid progress and inspiring numerous applications. However, for a WMN to be all it can be, considerable research efforts are still needed. The existing protocols need to be enhanced or re-invented for WMNs. We consider the WMN which is composed of current technology of networking of Internet, Wireless Local Area Networks (WLAN, typically IEEE 802.11 network) and Wireless Metropolitan Area Networks (WMAN, typically IEEE 802.16 network). Our research starts from bandwidth measurement in Internet, analysis and modification of existing wireless networks especially for IEEE 802.11 networks and IEEE 802.16 networks. The research topics and contributions of this dissertation focus on three aspects. Chapter 2 studies a set of novel and efficient algorithms for link capacity and available bandwidth detection over Internet. We focus on per link capacity detection and end-to-end available bandwidth measurement. The novelty and contributions of our algorithms are: (1) Efficiency: Our algorithms can effectively detect all the link capacities and available bandwidth for a given path with light load and short time duration; (2) Accuracy: via integrating measurement of link capacity, error control and cancellation, our algorithms can avoid error propagation problem and achieve high accuracy for the detections; (3) Adaptation: through combining both link capacity and available bandwidth detections, our algorithms can adaptively send the probing traffic in response to network load or the requirements of applications and we analyze the estimate errors even in the presence of layer-2 devices which are effectively “invisible” to IP and higher-layer protocol because they do not update the TTL field of the IP header.

Date of Award	3 Oct 2006
Original language	English
Awarding Institution	City University of Hong Kong
Supervisor	Wei Jia JIA (Supervisor)