Distributed middleware architectures for scalable media services

  • Authors:

  • V. Kalogeraki;D. Zeinalipour-Yazti;D. Gunopulos;A. Delis

  • Affiliations:

  • Department of Computer Science and Engineering, University of California-Riverside, Riverside, CA;Department of Computer Science and Engineering, University of California-Riverside, Riverside, CA;Department of Computer Science and Engineering, University of California-Riverside, Riverside, CA;Department of Informatics and Telecommunications, University of Athens, Athens, Greece

  • Venue:
  • Journal of Network and Computer Applications - Special issue: Network and information security: A computational intelligence approach
  • Year:
  • 2007

Quantified Score

Hi-index 0.00

Visualization

Abstract

The fusion of Multimedia and Internet technology has introduced an ever-increasing demand for large-scale reliable media services. This exposes the scalability limitations of current middleware architectures, as they traditionally operate on either very large-server configurations or on tightly coupled distributed systems. On the other hand, the wide availability of high-speed networks and the widespread deployment of powerful personal computing units by end users, has emphasized the advantages of the peer-to-peer (P2P) computing model. In this paper, we evaluate a number of different middleware architectures that facilitate the timely and reliable delivery of media services in P2P networks. Our evaluated architectures exploit features including availability of high-performance links, replication and caching of popular items and finally state-of-the-art search techniques proposed in the context of structured and unstructured P2P overlay networks. Through detailed simulation we investigate the behavior of the suggested P2P architectures for video provision and examine the involved trade-offs. We show that under realistic assumptions, the evaluated architectures are resilient to multiple peer-failures, are scalable with respect to dropped requests when the number of messages in the network increases and provide good response times to the user requests.