How Scalable Could P2P Live Media Streaming System Be with the Stringent Time Constraint?
How Scalable Could P2P Live Media Streaming System Be with the Stringent Time Constraint?
复制标题
DOI：
10.1109/icc.2009.5199057
复制
发表时间：
2009-06
期刊：
影响因子：
--
通讯作者：
Zhijia Chen;Bo Li;G. Y. Keung;H. Yin;Chuang Lin;Yuanzhuo Wang
中科院分区：
文献类型：
--
作者：
Zhijia Chen;Bo Li;G. Y. Keung;H. Yin;Chuang Lin;Yuanzhuo Wang
点对点（P2P）直播视频流系统已被证明在公共互联网中具有巨大的潜力；然而，此类系统的大规模部署关键取决于它们如何有效地应对遇到的高动态，特别是在闪光人群期间。其背后的基本原理是，P2P 实时视频流系统的扩展很大程度上取决于流应用程序所需的时序要求。在本文中，我们对时间约束与系统规模之间的内在关系进行了分析和实验研究。我们开发了一个 P2P 实时视频流的通用模型，重点关注闪存人群中的点对点加入过程。我们首先说明“需求与供给”模型的简单概念不足以描述系统规模。通过计算对等启动时间分布，我们证明了规模受到几个关键因素的影响，特别是对等上传容量和初始系统大小。我们进一步表明，规模本质上受到时序要求的限制，并且系统容纳闪存人群的能力受到最大限制。
The Peer-to-Peer (P2P) live video streaming system has been demonstrated to have great potential in the public Internet; the large-scale deployment of such systems, however, critically relies on how effective they can deal with the high dynamics encountered, in particular during flash crowd. The rationale behind is that the scaling in P2P live video streaming systems is heavily determined by the timing requirement that streaming applications demand. In this paper, we present an analytical and experimental study on the inherent relationship between the time constraint and the system scale. We develop a generic model for P2P live video streaming that focuses on the peer joining process during flash crowd. We first illustrate that the simple notion of "demand vs. supply" model is insufficient in describing the system scale. By computing the peer start-up time distribution, we demonstrate that the scale is affected by several key factors, especially the peer uploading capacity and the initial system size. We further show the scale is essentially bounded by the timing requirement and the system's capability to accommodate flash crowd is subject to a maximum limit.