The Third Annual Conference
of the TeleLearning Network of Centres of Excellence
November 14-17, 1998
Vancouver BC

Characterizing Traffic in a TeleLearning Environment Project 5.1
Multimedia Systems Architecture for Multimedia
Velibor Markovski and Ljiljana Trajkovic School of Engineering Science, Simon Fraser University

Traffic characterization of high-speed networks has only recently been shown to be promising due to the presence of the traffic "invariants" detected in traffic traces. Even with the availability of the emerging traffic models, it is not yet known what impact they will play on designing and provisioning data networks, and on selecting optimal connection admission and congestion control algorithms. The goal of this research is to answer some of these questions.

Our project goal is to characterize, model, and analyze traffic traces collected and measured from high-speed communication networks, such as the SFU's TeleLearning NCE and the Internet World Wide Web servers. Today's multimedia applications, such as those used in the TeleLearning environment, produce complex traffic patterns that result from the statistically multiplexed data, voice, image, and video patterns. For networks carrying such diverse applications, traditional traffic models have proved inadequate and incapable of capturing essential characteristics of the traffic patterns. In particular, we are interested in the analysis of collected data, which involves new statistical approaches and the search for traffic invariants such as self-similarity and long-range dependencies, as well as the understanding of underlying dynamical behavior of the complex system represented by collected data.

Collection of traffic traces from the TeleLearning network and their subsequent analysis will help to better understand the current performance issues of the TeleLearning research network. Better understanding of network usage, through collecting and monitoring of its traffic data, will help to choose appropriate network architecture and the design of protocols for video applications. Another important and useful outcome will be a collection of usage statistics and traffic from a real-life working network with multimedia applications.