Strategies of Collaboration in Multi-Swarm Peer-to-Peer Content Distribution

作     者：Zhi Wang Chuan Wu Lifeng Sun Shiqiang Yang 

作者机构：Tsinghua National Laboratory for Information Science and TechnologyDepartment of Computer Science and TechnologyTsinghua UniversityBeijing 100084China Department of Computer ScienceThe University of Hong KongPokfulamHong KongChina 

出 版 物：《Tsinghua Science and Technology》 (清华大学学报（自然科学版（英文版）)

年 卷 期：2012年第17卷第1期

页      面：29-39页

核心收录：

学科分类：0810[工学-信息与通信工程] 12[管理学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 08[工学] 081001[工学-通信与信息系统] 081201[工学-计算机系统结构] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：Supported by the National Basic Research and Development (973) Program of China (No. 2011CB302206) the National Natural Science Foundation of China (Nos. 60833009 and 60933013) the Research Grants Council of Hong Kong (RGC GRF Ref: HKU718710E) 

主　　题：Peer-to-Peer (P2P) networks content distribution inter-swarm collaboration media streaming 

摘      要：In modern Peer-to-Peer （P2P） content distribution applications, multiple swarms typically exist, each corresponding to the dissemination of one content among interested peers. A common design in the existing P2P applications is to allow peers in one swarm to help each other, while different swarms are only coupled when sharing the upload bandwidth at the dedicated content servers/publishers. In recent years, a number of proposals have emerged which advocate inter-swarm collaboration and resource sharing, where peers in one swarm may contribute their storage and bandwidth resources to help peers in the swarm of another content. Such inter-swarm collaboration can improve content availability and optimize resource uti- lization in the entire system, at the cost of additional overhead for content preloading and inter-swarm coor- dination. This paper presents a survey of studies on effective inter-swarm collaboration mechanisms in the existing literature. This paper first discusses strategies of collaboration in P2P file sharing applications, and then presents multi-channel collaborative design for P2P live and Video-on-Demand （VoD） streaming. In particular, this paper elaborates our recent design of collaboration strategies among multiple streaming channels in a P2P VoD system, and shows that the server cost can be reduced by up to 25% while high streaming qualities are guaranteed in the entire system, even during extreme scenarios such as unexpected flash crowds. This paper also discusses representative approaches to implement inter-swarm collaborations in various P2P content distribution systems.