On lifetime-based node failure and stochastic resilience of decentralized peer-to-peer networks
SIGMETRICS '05 Proceedings of the 2005 ACM SIGMETRICS international conference on Measurement and modeling of computer systems
On the minimum delay peer-to-peer video streaming: how realtime can it be?
Proceedings of the 15th international conference on Multimedia
Epidemic live streaming: optimal performance trade-offs
SIGMETRICS '08 Proceedings of the 2008 ACM SIGMETRICS international conference on Measurement and modeling of computer systems
Understanding the Power of Pull-Based Streaming Protocol: Can We Do Better?
IEEE Journal on Selected Areas in Communications
| Hi-index | 0.00 |
In a peer-to-peer (P2P) live streaming system, the streaming quality of an end user is much affected by the aggregate download bandwidth from the partners. In this paper, we propose a stochastic model for the P2P streaming system to analyze the asymptotic probability distribution of the aggregate download bandwidth of a peer. Using renewal theory, we derive a close form expression for the asymptotic mean and variance of the aggregate download bandwidth. We analyze the relationship between the distribution of the aggregate download bandwidth and peer dynamics, bandwidth heterogeneity as well as algorithm design. We show that reducing the partner search time and increasing the peer degree can bring better performance. We also analyze the effect of the local optimization procedure that is adopted by most P2P streaming systems. We find that local optimization can only redistribute the bandwidth resources among peers with different life time. We validate our findings through extensive simulations and the results show that our model can describe the bandwidth distribution with good accuracy.