Peer-Paired collaboration for on-demand streaming applications and an improved error recovery technique

Previous studies on streaming media networks have mainly focused on how to conserve the network bandwidth, especially the Internet backbone bandwidth, while maintaining a desired quality. This paper tackles the problem from another perspective, trying to improve the individual streaming quality while not increasing the backbone traffic. Specifically, we apply a peer-paired collaborative streaming architecture that exploits the power of peer-to-peer networking and extends the peer-paired colaboration from a live broadcasting scenario to the more general on-demand streaming scenario by introducing a unique catch-up scheme. Experimental results show that the peer-paired collaboration can bring about a significant performance gain for on-demand streaming application scenarios. In addition, we propose a forward error correction based error recovery technique that can resist up to 50% packet losses regardless of whether the losses are independent or shared.