Optimal peer selection for minimum-delay peer-to-peer streaming with rateless codes

  • Authors:
  • Chuan Wu;Baochun Li

  • Affiliations:
  • University of Toronto, Toronto, Canada;University of Toronto, Toronto, Canada

  • Venue:
  • Proceedings of the ACM workshop on Advances in peer-to-peer multimedia streaming
  • Year:
  • 2005

Quantified Score

Hi-index 0.00

Visualization

Abstract

Due to the limitation of peer upload capacities and high bandwidth demand of multimedia applications, optimal peer selection to construct high-quality streaming topology represents a major challenge in peer-to-peer streaming. In this paper, we propose a fully distributed algorithm to achieve optimal peer selection and streaming rate allocation, which minimizes end-to-end latencies in the streaming sessions. We design this efficient distributed algorithm based on the solution to a linear optimization model, which optimizes towards a latency-related objective to decide the best streaming rates among peers. Combining this optimal peer selection algorithm with our coding scheme based on rateless codes, we obtain a complete, fully decentralized minimum-delay peer-to-peer streaming scheme. Our scheme is resilient to network dynamics that is characteristic in peer-to-peer networks. The validity and effectiveness of our approach are demonstrated in extensive simulations.