Distributed Error Recovery for Continuous Media Data in Wide-Area Multicast

  • Authors:
  • Matthew T. Lucas;Bert J. Dempsey;Alfred C. Weaver

  • Affiliations:
  • -;-;-

  • Venue:
  • Distributed Error Recovery for Continuous Media Data in Wide-Area Multicast
  • Year:
  • 1995

Quantified Score

Hi-index 0.00

Visualization

Abstract

This paper proposes new mechanisms to improve the quality of wide-area disseminations of time-sensitive streams, such as packet voice and video, from a single source to multiple receivers. Most current packet-switched networks provide no end-to-end quality-of-service guarantees for packet delay or loss, which can reduce the playback quality at receivers. Buffering at the multicast receivers can be used to minimize the playback degradation due to network delay variations. Addressing packet losses is more problematic. Solutions are constrained by the long latencies that may exist between the source and some of its receivers, the danger of simultaneous messages from a large number of receivers overwhelming network and endsystem resources (multicast implosion), and the limited bandwidth available on most wide-area links. Adapting the transmission rate of the multicast source to the available network bandwidth prevents excessive packet loss and protects the network from severe congestion due to any single source. However, rate control does not recover packet losses. To recover packets dropped by the network, the transmission of redundant information in the data stream (forward error correction) has been shown effective, but redundancy may consume significant network bandwidth and is inefficient when receivers have heterogeneous error rates. In this paper we develop and evaluate a novel retransmission-based error recovery strategy. Unlike previous reliable multicast protocols, our protocol relies on retransmissions from one receiver to another, thus avoiding the limitations of long latencies and multicast implosion inherent to source-driven retransmissions. Local retransmissions enables low latency recovery, uses wide-area bandwidth sparingly, and isolates the impact of losses to one area of the network. Simulation results presented in this paper demonstrate that this retransmission-based scheme can achieve distributed and effective recovery of packet losses for large receiver sets. The results show further that network resources are efficiently utilized and compare favorably with utilization under forward error correction.