We develop a simple stochastic fluid model that seeks to expose the fundamental characteristics and limitations of P2P streaming systems. This model accounts for many of the essential features of a P2P streaming system, including the peers' realtime demand for content, peer churn (peers joining and leaving), peers with heterogeneous upload capacity, limited infrastructure capacity, and peer buffering and playback delay. The model is tractable, providing closed-form expressions which can be used to shed insight on the fundamental behavior of P2P streaming systems. The model shows that performance is largely determined by a critical value. When the system is of moderate-to-large size, if a certain ratio of traffic loads exceeds the critical value, the system performs well; otherwise, the system performs poorly. Furthermore, large systems have better performance than small systems since they are more resilient to bandwidth fluctuations caused by peer churn. Finally, buffering can dramatically improve performance in the critical region, for both small and large systems. In particular, buffering can bring more improvement than can additional infrastructure bandwidth.

No abstract

In this paper we present a scalable model of a network of Active Queue Management (AQM) routers serving a large population of TCP flows. We present efficient solution techniques that allow one to obtain the transient behavior of the average queue lengths, packet loss probabilities, and average end-to-end latencies. We model different versions of TCP as well as different versions of RED, the most popular AQM scheme currently in use. Comparisons between our models and ns simulation show our models to be quite accurate while at the same time requiring substantially less time to solve, especially when workloads and bandwidths are high.

Abstract. P2P streaming has been popular and is expected to attract even more users. One major challenge for P2P streaming is to offer users satisfactory Quality of Experience (QoE) in terms of video resolution, startup delay, and playback smoothness, all require efficient utilization of bandwidth resources in P2P networks. In this paper, we propose AQCS, adaptive queue-based chunk scheduling, that can support the maximum streaming rate allowed by a P2P streaming system with small signaling overhead and short startup delay. AQCS is a distributed algorithm with minimum requirement on peers. Queue-based design enables peers to be self-adaptive to the bandwidth variations and peer churn, and automatically converges to the optimal operating point. The prototype of AQCS is implemented and various implementation issues are examined. The experiments over the PlanetLab further demonstrate AQCS's optimality and its robustness against changing system/network environment.

Abstract-Peer-to-Peer (P2P) technology has recently been employed to deliver large scale video multicast services on the Internet. Considerable efforts have been made by both academia and industry on P2P streaming design. While academia mostly focus on exploring design space to approach the theoretical performance bounds, our recent measurement study on several commercial P2P streaming systems indicates that they are able to deliver good user Quality of Experience with seemingly simple designs. One intriguing question remains: how elaborate should a good P2P video streaming design be? Towards answering this question, we developed and implemented several representative P2P streaming designs, ranging from theoretically proved optimal designs to straightforward "naive" designs. Through an extensive comparison study on PlanetLab, we unveil several key factors contributing to the successes of simple P2P streaming designs, including system resource index, sever capacity and chunk scheduling rule, peer download buffering and peering degree. We also identify regions where naive designs are inadequate and more elaborate designs can improve things considerably. Our study not only brings us better understandings and more insights into the operation of existing systems, it also sheds lights on the design of future systems that can achieve a good balance between the performance and the complexity.