Li Lao (UCLA)

Thu, May 26
2:00 PM PDT
hosted by Aaron Falk

TOMA: A Viable Solution for Large-Scale Multicast Service Support

As an efficient mechanism to support group communication applications, multicast solutions have been evolving from "bottom" to "top", i.e., from IP layer to application layer. Recently, there are some new proposals (called overlay multicast) using certain "infrastructures" composed of proxies in the middle. However, little research has been done to systematically evaluate and compare the performance of these solutions, and many important questions are still open, such as which way to go: top, bottom, or in the middle?

We have conducted a comparative study to identify the key trade-offs of these three multicast architectures. Our study suggests that application layer multicast is a suitable solution for immediate deployment, whereas overlay multicast could serve as a long-term solution. Inspired by this discovery, we propose a Two-tier Overlay Multicast Architecture (TOMA) to provide scalable and efficient multicast support for various group communication applications. In TOMA, Multicast Service Overlay Network (MSON) is advocated as the backbone service domain, while end users in the access domains form a number of small clusters, in which an application-layer multicast protocol is used for the communication between the clustered end users.

In this talk, I will summarize our recent comparative study on different multicast architectures, present the TOMA solution, and highlight the major design challenges of TOMA. I will also elaborate some key techniques we propose in an effort to make TOMA a viable solution.

Bio

Li Lao is a PhD candidate in Computer Science Department at University of California, Los Angeles. She received her B.S. degree from Fudan University, China in 1998, and her M.S. degree from University of California, Los Angeles in 2002. Her research focuses on multicasting, overlay network management, network modeling and performance evaluation.