Employing Data Driven Random Membership Subset Algorithm for QoS-Aware Peer-to-Peer Streaming

  • Authors:
  • Huang Yongxiang;Qian Depei;Wu Weiguo;Zhao Haixiang

  • Affiliations:
  • Computer Department of Xi'An Jiaotong University, Xi'An, CHN 710049;Computer Department of Xi'An Jiaotong University, Xi'An, CHN 710049 and Sina-German Software Institute of BeiHang University, BeiJing, CHN 100076;Computer Department of Xi'An Jiaotong University, Xi'An, CHN 710049;Computer Department of Xi'An Jiaotong University, Xi'An, CHN 710049

  • Venue:
  • FMN '09 Proceedings of the 2nd International Workshop on Future Multimedia Networking
  • Year:
  • 2009

Quantified Score

Hi-index 0.00

Visualization

Abstract

Peer-to-peer (P2P) applications such as media broadcasting and content distribution often require that an overlay be constructed, and that some form of node selection take place over that overlay. Previous approaches to building such overlays focused mainly on high performance (leading to a rather brittle network of connections), or robustness (leading to low performance). In this paper, we present a data driven random membership (DDRM) algorithm, which tries to find a balance between the two, selecting peers for performance when needed, and at random (for robustness) if possible. The simulation experiment results show that the algorithm is not only QoS-Aware, but also ensures the scalability and good connectivity of the overlay.