同构流媒体集群系统优化内容部署

卫星; 杨坚; 奚宏生

doi:10.3724/SP.J.1146.2008.01267

同构流媒体集群系统优化内容部署

doi: 10.3724/SP.J.1146.2008.01267

计量
- 文章访问数: 2986
- HTML全文浏览量: 70
- PDF下载量: 769
- 被引次数: 0
出版历程
- 收稿日期: 2008-10-06
- 修回日期: 2009-04-06
- 刊出日期: 2009-09-19

Optimal Content Distribution on Clustered Streaming Media System Consisting of Homogeneous Configuration

摘要

摘要: 该文研究了在固定节目流行度的情况下，如何进行内容优化部署以最小化流媒体集群系统拒绝率和降低复制存储消耗的问题。首先运用排队理论知识分析得出优化目标和服务器访问概率之间的数值联系，并且通过某些数值方法确定出系统最小拒绝率情况下的最优服务器访问概率。由于内容部署属于NP-Hard问题且完全决定每台服务器的访问概率，该文设计了副本交换和对等副本访问概率调整两种启发式策略来进行内容部署，以满足在优化内容分布下每台服务器访问概率和最优值之间的差异最小，从而实现降低系统拒绝率和存储代价的目标。最后分别采用数值分析和离散事件仿真验证了模型的正确性和算法的有效性。
- 流媒体集群系统; 内容部署; 存储均衡; 拒绝率
Abstract: The optimizing problem of content distribution which minimizes the blocking probability and storage consumption on clustered streaming media system is discussed, in the case of knowing every programs unchanged popularity. Firstly, the queuing theory is adopted to analysis the relationship between the servers access probability and the optimizing goal. The ideal access probability of every server can be obtained by some numerical methods, under the circumstance of minimal blocking probability. Content distribution determining each servers access probability, has been proved to be NP-Hard. The whole content distribution process consists of two strategies, i.e. duplicate swapping and peer duplicates access probability adjusting. All the heuristic arithmetic is designed to perform the content distribution in order to minimize the distance between the result of optimization and the ideal one, minimize the storage consumption and reduce the blocking probability. Finally, the correctness of system modeling and the efficiency of proposed arithmetic are verified by numerical analysis and discrete event simulation.

HTML全文

参考文献(1)

Dakshayini M, Guruprasad H S, and Masheshappa H D, et al..Load balancing in distributed VoD using Local Proxy ServerGroup(LPSG). IEEE International Conference onComputational Intelligence and Multimedia Application,Sivakasi, Tamil Nadu, 13-15 Dec. 2007, 4: 162-168.[2]Zhang Ming-long and Feng Bo-qin. A novel migrationalgorithm based-on states-balancing in a distributedmultimedia services system. International Conference onMultimedia and Ubiquitous Engineering, Busan, 24-26 April2008: 336-341.[3]Leung Yiu-wing and Hou Yuen-tan. Assignment of movies toheterogeneous video servers[J].IEEE Transactions on Systems,Man, and Cybernetics-Part A.2005, 35(5):665-681[4]Jun Guo, Wong E W M, and Chan S, et al.. Combination loadbalancing for video-on-demand system[J].IEEE Transactionson Circuits and Systems for Video Technology.2008, 18(7):937-948[5]Serpanos D N, Georgiadis L, and Bouloutas T. MMPacking:A load and storage balancing algorithm for distributedmultimedia servers[J].IEEE Transactions on Circuits andSystems for Video Technology.1998, 8(1):13-17[6]Zhao Yin-qing and Kuo C C J. Scheduling design fordistributed video-on-demand servers. IEEE InternationalSymposium on Circuits and System, Kobe, Japan, 2005, 2:1545-1548.[7]Zhao Yin-qing and Kuo C C J. Design issues on requestmigration for video-on-demand services. Proceedings of the2004 International Symposium on Circuits and Systems,23-26 May 2004, 2: 49-52.[8]Tang Kit-sang, Ko King-tim, and Chan Sammy, et al..Optimal file placement in VOD system using geneticalgorithm[J].IEEE Transactions on Industrial Electronics.2001,48(5):891-897[9]Zhou Xiao-bo and Xu Cheng-zhong. Optimal videoreplication and placement on a cluster of video-on-demandservers. IEEE International Conference on ParallelProceeding, Vancouver Canada, 18-21 Aug. 2002: 547-555.[10]Gross D and Harris C M. Fundamentals of Queueing Theory.New York, Wiley, 1985: 294-304.

施引文献

资源附件(0)

访问统计