A Scaleable Multicast Protocol to Enable Future-Generation Large Scale Multimedia Applications

The University Of Central Florida Board Of Trustees, Orlando FL

Investigators

Abstract

A picture is worth a thousand words, and the addition of sound and motion can breathe life into a picture. As a result, the use of video in all kinds of multimedia applications has become an important development in the 1990s. In particular, Video on demand (VOD) is a core technology for many important applications such as digital libraries, distance learning, electronic commerce, entertainment, public information systems, etc. The simplest video delivery technique employs a dedicated stream for each service request. Obviously, this scheme is too expensive and has been shown to have little scalability. To vastly reduce this cost, one can leverage multicast technology to allow multiple clients to share a video stream. Unfortunately, today's multicast technology was developed in the 80's, and was not optimized for such applications. Missing a multicast could mean a long wait until the next multicast. This limitation has recently led to a large body of research looking for remedies at the application level. Application-level solutions, however, cannot address all the drawbacks, particularly traffic congestion caused by too many multicasts. In fact, this proposal is motivated by application-level work done by the investigator in his last NSF project (from 1998 to 2000). The achievements of that project, though significant, were constrained by the limitation of standard multicast. Minimizing the multicast frequency is crucial for any multicast-based applications, particularly those running on a public network such as the Internet. Attaining this goal requires a fundamental change in the multicast concept. The investigator proposes enabling the multicast tree to deliver the entire video to all the receivers who may subscribe to the multicast at different times. This new capability would significantly reduce the number of multicasts necessary, and therefore lower the network resource requirements. At first sight, this seems like a mission impossible. But on the contrary, this can be achieved by allowing the routers on the multicast tree to intercept and cache a video stream passing through. The data can be relayed to subsequent subscribers to further extend the multicast tree. In this project, the investigator proposes to develop a suite of techniques to make such an environment practical for future-generation large-scale multimedia applications. To assess the potential of the proposed idea, the investigator has designed an initial version of his Caching Multicast Protocol (CMP). The preliminary study indicates that this approach has the potential to revolutionize the way in which multimedia information is disseminated. This scheme is much more scalable and less expensive than application-level solutions. The new communication paradigm, however, demands new research at the network level. In this project, the investigator proposes to study issues such as cache organization, cache replacement policies, multicast routing algorithms, congestion control, client and server protocols, etc. In addition, he will implement a prototype, consisting of CMP-capable routers, CMP-compliant servers (sources) and CMP-compliant clients (destinations) to examine the practicality of the proposed techniques. The significance of this project is in advancing multicast technology to enable large-scale deployment of multimedia applications. Although many great advances have been made in the field of information technology, none have had as great and direct an impact on the daily lives of ordinary citizens as multime-dia information systems. As such, the benefits of this research will reach many people in society. In terms of education, this project will help to support three doctoral students. The investigator has a good record of using NSF projects to train students for teaching careers. After these students graduate, they can help to spread the CMP expertise developed from this project to their new institutions. Other graduate students taking our advanced databases course can also benefit from this work by experimenting with various new multicast applications on the CMP testbed. To reach out to members of communities, materials resulting from this research will be disseminated on the investigator's research group website.