A dynamically grouped multi-multicast stream scheduling strategy for video-on-demand systems

  • Authors:

  • Dafu Deng;Hai Jin;Zongfen Han

  • Affiliations:

  • Huazhong University of Science and Technology, Wuhan, China;Huazhong University of Science and Technology, Wuhan, China;Huazhong University of Science and Technology, Wuhan, China

  • Venue:
  • ICCS'03 Proceedings of the 2003 international conference on Computational science: PartII
  • Year:
  • 2003

Quantified Score

Hi-index 0.00

Visualization

Abstract

Network bandwidth is the key performance bottleneck for a videoon-demand (VoD) server. It controls the number of clients the server can support simultaneously. Previous works have shown some strategies, such as the batching strategy and the stream merging strategy, that use one multicast stream to serve different clients requesting the same video object at the same time. They improve the performance of server bandwidth effectively. But the batching strategy results in long start-up latency and the traditional stream merging strategy also wastes lots of server bandwidth. In this paper, we propose a dynamically grouped multi-multicast stream scheduling strategy, called DGMM, and analyze its performance in two factors: the start-up latency and the average bandwidth consumption.