支援隨選視訊服務的點對點多層疊加網路架構

簡易檢索 / 詳目顯示

回結果列表

研究生：	周彥廷 Yen-Ting Chou
論文名稱：	支援隨選視訊服務的點對點多層疊加網路架構 A Peer-to-Peer Multi-Overlay Network Supporting Video-on-Demand Services
指導教授：	石維寬 Wei-Kuan Shih
口試委員:
學位類別：	碩士 Master
系所名稱：	電機資訊學院 - 資訊系統與應用研究所 Institute of Information Systems and Applications
論文出版年：	2005
畢業學年度：	93
語文別：	英文
論文頁數：	72
中文關鍵詞：	點對點運算、隨選視訊、多層疊加網路、聚集頻寬
外文關鍵詞：	Peer-to-Peer computing, Video-on-Demand, multi-overlay networks, aggregate bandwidth
相關次數：	點閱：4 下載：0
分享至:	分享至facebook 分享至twitter

查詢本校圖書館目錄查詢臺灣博碩士論文知識加值系統勘誤回報

　　以點對點 (peer-to-peer) 技術來實現隨選視訊服務 (video-on-demand services) 可獲得多項益處，例如將負載平均地分配至各個節點上，並妥善利用各個節點間的網路頻寬，進而降低單一中央視訊伺服器 (video servers) 之負擔。在這篇論文中，我們提出了一個基於多層疊加網路 (multi-overlay networks) 觀念的新穎點對點網路架構，稱之為MegaDrop，並利用其建構出一個完全分散化的網路環境，有效地提供隨選視訊服務。

　　在傳統使用點對點技術設計的隨選視訊系統中，通常僅考慮主動參與同一視訊流傳輸 (video streaming) 之使用者，並於該群節點間互相傳遞串流資料；然而這些研究皆未考慮那些已結束視訊流之傳送但仍擁有片段視訊資料的使用者。我們所提出的架構中則涵蓋此項因素的考量，進一步提供搜尋機制來發掘其它同位於MegaDrop網路上，且擁有目標視訊物件的潛在使用者。

　　由於硬體技術持續的進步，使用者設備端所擁有的磁碟空間、處理運算能力亦明顯增進。本研究即充份利用此項優勢，分散視訊資料至各個使用者身上，允許任一使用者快速地在此點對點網路中搜索特定視訊物件，並同時自多個節點上接收視訊片段直到完整資料傳輸完成為止。串流議程 (streaming session) 中完全無中央視訊伺服器存在之觀念，進而規避了單點故障風險 (single point of failure)。

　　研究中採用了分層概念將架構劃分為四個子層：節點探索層 (Peer Discovery Layer)、內容搜尋層 (Content Lookup Layer)、媒體串流層 (Media Streaming Layer)、錄放控制層 (Playback Control Layer)。節點探索層負責發掘其它同位於 MegaDrop 網路上的節點，其建構了第一層疊加網路；內容搜尋層建立每項視訊物件的唯一識別，以快速地提供內容比對功能；媒體串流層處理使用者間的實際資料傳輸，其建構了第二層疊加網路；錄放控制層則提供視訊操作介面，讓使用者可播放、控制傳輸中的視訊資料。

　　從實作系統的效能評估結果可得，我們所提出的架構用於大型視訊資料傳輸與多人串流協議特別有效率。愈多使用者參與同一視訊流的傳送，使用者間的聚集頻寬 (aggregate bandwidth) 將有效地獲得提升，進而降低平均串流時間。此外，實作之系統不僅適用於隨選視訊傳輸，其亦適合提供節點間的檔案分享 (file sharing) 服務。

　　Video-on-Demand (VoD) services using peer-to-peer (P2P) technologies benefit by balancing load among clients and maximizing their bandwidth utilization to reduce the burden on central video servers. In this thesis, we propose a novel architecture to construct a fully decentralized P2P overlay network for VoD streaming based on a multi-overlay concept. The architecture is referred to as MegaDrop.

　　Conventional P2P techniques for realizing VoD services only stream media data between active peers in the same VoD session. However, they never consider those inactive peers that have left the session but may still hold partial media content in their local storage. Thus, our architecture takes both kinds of peers into consideration, providing mechanisms for discovering all potential nodes that may possess the desired media objects.

　　By taking advantage of the large storage and the powerful processing capability in current client-side devices, the architecture distributes media among nodes, allows any peer to search for a specific media object over the entire P2P network as soon as possible, and streams the media object from a group of the nodes that have either the entirety or only parts of the media content. There is no central resource allocation in the streaming session at all, thereby avoiding the single point of failure.

　　We employed a layering strategy further dividing the architecture into four major tiers: Peer Discovery Layer (PDL), Content Lookup Layer (CLL), Media Streaming Layer (MSL), and Playback Control Layer (PCL). PDL takes charge of discovering peers, which constructs the first overlay network. CLL generates a unique identifier for a media object and provides content matching capability. MSL performs actual media transmission between peers, which constructs the second overlay network. PCL interacts with end users, letting them execute control operations.

　　The evaluation of the resultant system revealed that our architecture is particularly efficient for huge media delivery and multi-user streaming session. The more peers participating in a session, the more aggregate bandwidth peers can obtain. All of the peers thereby gain a shorter average streaming time. Furthermore, our system provides not only VoD streaming but also file sharing services.

中文摘要 …………………………………………………………I
Abstract …………………………………………………………II
Acknowledgements ………………………………………………III
Table of Contents …………………………………………… IV
List of Figures ……………………………………………… VI
List of Tables …………………………………………………VII
Chapter 1　Introduction …………………………………… 1
　1-1　Background …………………………………………… 1
　1-2　Objectives …………………………………………… 2
　1-3　Disposition ……………………………………………3
Chapter 2　Related Work …………………………………… 4
　2-1　Overlay Networks …………………………………… 4
　2-2　Overview of P2P Architectures ……………………4
　2-3　Semi-centralized Architectures ………………… 5
　2-4　Decentralized Architectures ………………………6
　2-5　Unstructured Decentralized Architectures …… 6
　2-6　Structured Decentralized Architectures ……… 8
　　2-6-1　Chord ………………………………………………8
　　2-6-2　Pastry …………………………………………… 9
　　2-6-3　CAN …………………………………………………10
　　2-6-4　Discussion ……………………………………… 11
　2-7　Hierarchical Architectures ……………………… 12
　　2-7-1　Gnutella2 …………………………………………12
　2-8　VoD Streaming with P2P Model …………………… 14
　　2-8-1　Chaining ………………………………………… 15
　　2-8-2　DirectStream …………………………………… 16
　　2-8-3　P2Cast …………………………………………… 17
　　2-8-4　P2VoD ………………………………………………18
Chapter 3　Architecture …………………………………… 20
　3-1　Motivation …………………………………………… 20
　3-2　Multi-Overlay Networks …………………………… 21
　3-3　Layered Architecture ……………………………… 22
　3-4　Peer Discovery Layer ……………………………… 23
　3-5　Content Lookup Layer ……………………………… 25
　3-6　Media Streaming Layer ………………………………26
　3-7　Playback Control Layer …………………………… 27
Chapter 4　Implementation ………………………………… 29
　4-1　Development Environment ……………………………29
　4-2　Peer Discovery Layer ……………………………… 30
　　4-2-1　Bootstrapping ……………………………………30
　　4-2-2　Handshaking ………………………………………32
　　4-2-3　Messages ………………………………………… 34
　　4-2-4　Query Hash Tables ………………………………37
　　4-2-5　Query Routing ……………………………………38
　4-3　Content Lookup Layer ……………………………… 40
　　4-3-1　Media-hash ……………………………………… 40
　　4-3-2　Content Matching ……………………………… 42
　　4-3-3　Data Integrity ………………………………… 44
　4-4　Media Streaming Layer ………………………………44
　　4-4-1　Media-info ……………………………………… 45
　　4-4-2　Brokering …………………………………………46
　　4-4-3　Media Streaming …………………………………48
　　4-4-4　Buffer Management ………………………………51
　　4-4-5　Downstream Modes ……………………………… 52
　　4-4-6　Bartering …………………………………………52
　4-5　Playback Control Layer …………………………… 53
　　4-5-1　Source Filter ……………………………………53
　　4-5-2　Player Control ………………………………… 55
　4-6　Snapshots of MegaDrop ………………………………55
Chapter 5　Evaluation ……………………………………… 59
　5-1　Startup Delay …………………………………………59
　5-2　Overheads ………………………………………………61
　5-3　Aggregate Bandwidth …………………………………63
Chapter 6　Conclusion ……………………………………… 66
　6-1　Summary …………………………………………………66
　6-2　Future Work ……………………………………………68
References ………………………………………………………70

                                

[1] Walkerdine, J., Melville, L., Sommerville, I. Dependability within Peer-to-Peer Systems, In Proceedings of WADS 2004 (Edinburgh, UK, May 2004).
[2] Napster protocol specification, June 2000. http://www.napster.com/.
[3] Gnutella.http://www.gnutella.com/.
[4] I. Clark, O. Sandberg, B. Wiley & T. W. Hong. Freenet: a distributed anonymous information storage and retrieval system. International Workshop on Design Issues in Anonymity and Unobservability, LNCS 2009, Springer: New York (2001).
[5] Stoica, I., Morris, R., Karger, D., Kaashoek, M. F., and Balakrishnan, H. Chord: A scalable peer-to-peer lookup service for internet applications. In Proc. ACM SIGCOMM 2001.
[6] A. Rowstron and P. Druschel, "Pastry: Scalable, distributed object location and routing for large-scale peer-to-peer systems". IFIP/ACM International Conference on Distributed Systems Platforms (Middleware), Heidelberg, Germany, pages 329-350, November 2001.
[7] Ion Stoica, Robert Morris, David Karger, Frans Kaashoek, and Hari Balakrishnan. Chord: A scalable contentaddressable network. In Proceedings of the ACM SIGCOMM 2001 Technical Conference, San Diego, CA, USA, August 2001. Stefan Saroiu et al.
[8] Gnutella2. http://www.gnutella2.com/.
[9] E. Adar and B. Huberman, Free riding on Gnutella, Xerox PARC, Tech. Rep., 2000.
[10] M. Ripeanu, Peer-to-peer architecture case study: Gnutella network, University of Chicago, Tech. Rep., 2001.
[11] J. Ritter. Why Gnutella can't scale, Feb. 2001. http://www.darkridge.com/jpr5/doc/gnutella.html.
[12] B. Y. Zhao, J. D. Kubiatowicz, and A. D. Joseph. Tapestry: An infrastructure for fault-resilient wide-area location and routing. Technical Report UCB//CSD-01-1141, U.C. Berkeley, April 2001.
[13] C. G. Plaxton, R. Rajaraman, and A. W. Richa. Accessing nearby copies of replicated objects in a distributed environment. In Ninth annual ACM symposium on Parallel algorithms and architectures, pages 311--320, 1997.
[14] D. Malki, M. Naor, and D. Ratajczak, Viceroy: A scalable and dynamic emulation of the butterfly, Proceedings of the 21st ACM Symposium on Principles of Distributed Computing, 2002.
[15] KARGER, D., LEHMAN, E., LEIGHTON, F., LEVINE, M., LEWIN, D., AND PANIGRAHY, R. Consistent hashing and random trees: Distributed caching protocols for relieving hot spots on the World Wide Web. In Proceedings of the 29th Annual ACM Symposium on Theory of Computing (El Paso, TX, May 1997), pp. 654-663.
[16] M. Castro, P. Druschel, A. Kermarrec, and A. Rowstron. Scribe: A Large-Scale and Decentralized Application-Level Multicast Infrastructure. In IEEE Journal on Selected Areas in Communications Vol. 20 No. 8, Oct 2002.
[17] P. Druschel and A. Rowstron, "PAST: A large-scale, persistent peer-to-peer storage utility", HotOS VIII, Schoss Elmau, Germany, May 2001.
[18] S. Iyer, A. Rowstron and P. Druschel, "SQUIRREL: A decentralized, peer-to-peer web cache", appeared in Principles of Distributed Computing (PODC 2002), Monterey, CA.
[19] M. Castro, P. Druschel, A-M. Kermarrec, A. Nandi, A. Rowstron and A. Singh, "SplitStream: High-bandwidth multicast in a cooperative environment", SOSP'03,Lake Bolton, New York, October, 2003.
[20] Y. Chawathe, S. Ratnasamy, L. Breslau, N. Lanham, and S. Shenker, "Making Gnutella-Like P2P Systems Scalable," in Proc. of the 2003.
[21] M. Castro, M. Costa, and A. Rowstron. Should we build gnutella on a structured overlay? In Proceedings of HOTNETS II, 2003.
[22] Hughes, D., Coulson, G., Warren, I., "A Framework for Developing Reflective and Dynamic P2P Networks (RaDP2P)", Proceedings of the 4th IEEE International Conference on Peer-to-Peer Computing, Zurich, Switzerland, August 2004.
[23] Kien A. Hua, Mounir A. Tantaoui, "Cost Effective and Scalable Video Streaming Techniques," in Borko Furht, Oge Marques (eds.): Handbook of Video Databases CRC press, 2002.
[24] Simon Sheu, Kien A. Hua, Wallapak Tavanapong, "Chaining: A Generalized Batching Technique for Video-on-Demand Systems, in Proc. of the IEEE Int'l Conf. On Multimedia Computing and System, Ottawa, Ontario, Canada, June 1997, pp. 110 117.
[25] Yang Guo, Kyoungwon Suh, Jim Kurose, Don Towsley, "A Peer-to-Peer On-Demand Streaming Service and Its Performance Evaluation", Proceedings of 2003 IEEE International Conference on Multimedia & Expo (ICME 2003), Baltimore, MD, July 2003.
[26] Y. Guo, K. Suh, J. Kurose, and D. Towsley, "P2Cast: P2P patching scheme for VoD service," in Proc. Int. World Wide Web Conf., 2003, pp. 301-309.
[27] Tai T. Do, Kien A. Hua, Mounir Tantaoui. P2VoD: Providing Fault Tolerant Video-on-Demand Streaming in Peer-to-Peer Environment. In proc. of the IEEE International Conference on Communications, Paris, June 2004.
[28] Duc A. Tran, Kien A. Hua, Tai T. Do, "A Peer-to-Peer Architecture for Media Streaming," in IEEE Journal on Selected Areas in Communication, Special Issue on Advances in Overlay Network, 2003.
[29] GnucDNA. http://www.gnucleus.com/GnucDNA/.
[30] BNBT EasyTracker. http://bnbteasytracker.sourceforge.net/.
[31] DSPlayer. http://www.dsplayer.de/.
[32] Gnutella Web Caching System. http://www.gnucleus.com/gwebcache/.
[33] Christofer Rohrs. Query routing for the Gnutella network. http://rfc-gnutella.sourceforge.net, December 2001.
[34] BitTorrent Protocol. http://www.bittorrent.com/protocol.html.
[35] B. Cohen. Incentives build robustness in BitTorrent. In Proceedings of the First Workshop on the Economics of Peer-to-Peer Systems, Berkeley, CA, June 2003.
[36] Microsoft Developer Network (MSDN). http://msdn.microsoft.com/.
[37] S. Ratnasamy, M. Handley, R. Karp, and S. Shenker. Topologically-Aware Overlay Construction and Server Selection. In Proceedings of IEEE INFOCOM, 2002.

全文公開日期本全文未授權公開 (校內網路)
全文公開日期本全文未授權公開 (校外網路)
全文公開日期本全文未授權公開 (國家圖書館：臺灣博碩士論文系統)

簡易檢索 / 詳目顯示

相關論文