(3.236.222.124) 您好!臺灣時間:2021/05/08 07:37
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果

詳目顯示:::

我願授權國圖
: 
twitterline
研究生:林彥佑
研究生(外文):Yan-Yo Lin
論文名稱:多媒體串列流代理伺服器下之有效率的修補排程
論文名稱(外文):Efficient Patching Scheduling for Multimedia Streaming Proxy
指導教授:陳添福陳添福引用關係
指導教授(外文):Tien-Fu Chen
學位類別:碩士
校院名稱:國立中正大學
系所名稱:資訊工程研究所
學門:工程學門
學類:電資工程學類
論文種類:學術論文
論文出版年:2001
畢業學年度:89
語文別:英文
論文頁數:40
中文關鍵詞:串列流多點傳送修補技術修補排程
外文關鍵詞:streamingmulticastpatchingpatching scheduling
相關次數:
  • 被引用被引用:0
  • 點閱點閱:445
  • 評分評分:系統版面圖檔系統版面圖檔系統版面圖檔系統版面圖檔系統版面圖檔
  • 下載下載:0
  • 收藏至我的研究室書目清單書目收藏:2
這幾年來在網路上多媒體應用的普及可以說是呈現戲劇性的成長,但多媒體串列流本身需要很大量的傳輸頻寬,因此在對於如何減輕伺服器與網路頻寬的負荷上便有許多的方法陸續被提出,Patching是這許多方法的其中之一,它允許客戶端(client)藉由傾聽目前正在傳輸中且與需求相同的影片,而去接收所需要的多點播送串列流(multicast stream),以減少相同的影片片段再次由伺服器送出。Greedy Buffer Reuse (GBR)是Patching的一種演算法,它可以最小化伺服器與網路傳輸頻寬的需求。然而當多媒體串列流利用多點傳送的方式(multicast)送給許多客戶端時,客戶端必須要利用他本身有限容量的暫存器(buffer)儲存這些傳送過來的串列流的影像畫面,也因為有限容量的暫存器之故,使得傳送過來的串列流中部份的影像畫面(frame)無法順利存入客戶端的暫存器中而造成部份影像畫面的流失,於是這些失去的影像畫面就必須再由伺服器端重新取得,我們稱這些影像畫面為修補畫面(patching frames)。我們提出了一個稱做修補排程的演算法,它針對每一個修補畫面,考慮是否有辦法由目前的串列流中取得此一畫面並存入多媒體串列流代理伺服器(streaming proxy)中,這樣一來可以減少更多必須要到伺服器修補的畫面。另外當客戶端的要求頻繁時,會造成許多影片的起始畫面(prefix frames)需要由伺服端修補,這樣一來會減少修補排程的效能,對於這種特殊情況我們提出修補排程與只截取影片一開始的畫面這兩種方法的相互合作,共同利用代理伺服器的暫存空間,來達到改善修補排程的效能,而在我們實驗的結果也顯示,改善後的修補排程的確能在一部影片非常熱門時大量減輕伺服器與網路頻寬的負荷。

The popularity of Internet multimedia applications has grown dramatically in the past several years. The multimedia streaming demands high transmission bandwidth requirement. There are several methodologies about reducing the server workload and the network traffic has been published. Patching is one of these methodologies; it allows a client to receive a multicast stream by listening to an ongoing transmission of the same video clip to reduce frames transmitted from the server. Greedy Buffer Reuse (GBR) is a patching algorithm that minimizes the server and the network transmission bandwidth requirements. However, multimedia streams multicasting to clients must be stored in a client buffer with the limited size. The fractions of multimedia streaming will be lost due to the limited size of the client buffer. Those frames are called patching frames because the client needs to patch those frames from the server. We propose a patching scheduling algorithm to schedule each patching frame on the ongoing streaming cached in the proxy. This will further reduce frames that need to be patched from the server. Prefix frames patched from the server will be increased when requests arrive close. This may make the reduction ratio of patching scheduling down. In order to solve this particular circumstance, we present a patching scheduling with prefix caching mechanism. This mechanism is to share the space of the proxy cache for both patching scheduling and prefix caching. The simulation results show that the proxy can reduce large server overhead and network traffic under patching scheduling with prefix caching mechanism when a video clip is popular in the multimedia server.

1 Introduction................................................1
1.1 Motivation................................................1
1.2 Main contribution.........................................2
1.3 Thesis organization.......................................2
2 Background and Related Work.................................3
2.1 Quality adaptation........................................3
2.2 Easing server workload and network congestion.............4
2.2.1 Multicast...............................................4
2.2.2 Patching scheme.........................................5
2.3 Patching algorithm........................................6
2.4 Dynamic caching...........................................9
2.5 Prefix caching............................................10
3 Patching Scheduling of Streaming Proxy......................11
3.1 Overview of system architecture...........................11
3.2 Basis of Patching scheduling..............................12
3.2.1 An Example of GBR algorithm.............................15
3.3 Proposed proxy caching mechanism..........................17
3.3.1 Motivation of the patching scheduling...................18
3.3.2 Patching scheduling in the proxy........................19
3.4 Patching scheduling with prefix caching...................23
4 Performance Evaluation......................................28
4.1 Simulation environment....................................28
4.2 Patching scheme with varying buffer size and request rate.29
4.3 Effect of proxy cache size under proxy caching............30
4.4 Effect of request rate under proxy caching................31
4.5 Comparison between prefix caching and patching scheduling.33
4.6 Evaluation of hybrid approach.............................35
5 Conclusion..................................................37

[1] C. Aggarwal, J. Wolf, and P. Yu. On optimal batching policies for video-on-demand servers, 1996.
[2] E. Bommaiah, K.Guo, M.Hofmann, and S. Paul. Design and implementation of a caching system for streaming media over the internet, 1999.
[3] Stephane Gruber, Jennifer Rexford, and Andrea Basso. Protocol considerations for a prefix-caching proxy for multmedia streams. WWW9/Computer Networks, 33(1-6):657-668, 2000.
[4] M. Hofmann, E. Ng, K. Guo, S. Paul, and H. Zhang. Caching techniques for streaming multimedia over the internet, 1999.
[5] K. Hua, Y. Cai, and S. Sheu. Patching: A multicast technique for true video-on-demand services. In Proc. ACM Multimedia, September 1998.
[6] Z. Miao and A. Ortega. Proxy caching for efficient video services over the internet, 1999.
[7] R. Rejaie, M. Handley, H. Yu, and D. Estrin. Proxy caching mechanism for multimedia playback streams in the internet, 1999.
[8] Reza Rejaie, Mark Handley, and Deborah Estrin. Quality adaptation for congestion controlled video playback over the internet. In SIGCOMM, pages 189-200, 1999.
[9] S. Sen, L. Gao, J. Rexford, and D. Towsley. Optimal patching schemes for efficient multimedia streaming, 1999.
[10] Simon Sheu, Kien A. Hua, and Wallapak Tavanapong. Chaining: A generalized batching technique for video-on-demand. In International Conference on Multimedia Computing and System, pages 110-117, 1997.

QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top
系統版面圖檔 系統版面圖檔