實況與移時影音串流系統的實作與效能評估

點對點式網路架構目前廣泛應用於多媒體影音串流服務中，用以解決過去主從式網路架構所無法負荷的龐大流量。然而在點對點影音串流的蓬勃發展中，移時影音串流服務，也就是提供使用者觀看任意過去時間點上的影音串流服務的相關研究並不多。於此篇論文中，我們提出了一個數學模型來評估移時影音串流服務的可行性，並且實作了一支援移時服務的點對點實況串流系統。此系統提出針對移時串流影音資料的分散式快取管理解決策略，並加強移時影音用戶的合作關係以分散對於整體系統的負擔。最後我們在PlanetLab平台上進行實驗，分析整體系統的效能以及特性。在我們實驗中全部移時用戶錯過少於0.5%的影音片段，並且只有造成影音伺服器少於全部移時影音服務流量的3%的負擔。而移時串流訂閱機制使移時用戶直接分享正在觀看的影音內容，其中有30%的移時串流流量來自此種方式，並且降低了15%原本需由實況用戶提供的移時串流流量。我們相信這將提供此類系統的一般性了解，幫助我們進一步的發展多媒體串流服務。

關鍵字

移時串流；實況串流；點對點

並列摘要

Peer to peer (P2P) technologies have been applied to multimedia streaming services to solve the problem of heavy traffic flow on the servers in server-client architecture. However, there are few researches on the time-shifted streaming service, where viewers can choose an arbitrary offset of time to watch. In this thesis, we present a numeric model to analyze the feasibility conditions of the time-shifted streaming, and implement a P2P live and time-shifted streaming system. In this system, we propose a distributed cache management strategy for time-shifted streaming contents and enhance the cooperation among time-shifted peers to balance the traffic load in the system. Experiments were performed on PlanetLab to evaluate the system performance. Our experiment results show the feasibility of P2P time-shifted video streaming systems and the effectiveness of the proposed strategies. The video block missed rate of Time-shifter viewers is less than 0.5% and the server stress of time-shifted streams is less than 3% of all time-shifted traffic. By establishing supplier-subscriber relationship among time-shifted peers, more than 30% of the time-shifted streams are supplied by other time-shifted peers. This reduces 15% transmission load of time-shifted streams on live streaming peers.

並列關鍵字

time-shifted streaming ； live streaming ； peer-to-peer

參考文獻

[1] F. Douglis and M.F. Kaashoek, “Scalable Internet Services,” IEEE Internet Computing, vol. 5, no. 4, 2001, pp. 36–37.

[2] A. Vakali, and G. Pallis, “Content delivery networks: status and trends” IEEE Internet Computing, vol. 7, no. 6, 2003, pp. 68-74.

[3] Xinyan Zhang, et al., “CoolStreaming/DONet: a data-driven overlay network for peer-to-peer live media streaming” INFOCOM 2005. 24th Annual Joint Conference of the IEEE Computer and Communications Societies. Proceedings IEEE, vol. 3, pp. 2102-2111. Mar. 2005

[4] Li Zhao, et al., “Gridmedia: A Practical Peer-to-Peer Based Live Video Streaming System” Multimedia Signal Processing, 2005 IEEE 7th Workshop on, pp. 1-4. Nov. 2005

[5] Bo Li, et al., “Inside the New Coolstreaming: Principles, Measurements and Performance Implications” INFOCOM 2008. The 27th Conference on Computer Communications. IEEE, pp. 1031-1039, Apr. 2008

國際替代計量

實況與移時影音串流系統的實作與效能評估

全文下載

主題瀏覽