Please use this identifier to cite or link to this item:
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/47212
Title: | 雲端端對端:在雲端輔助之端對端系統下節省成本 CloudP2P: Saving Cost in Cloud-Assisted Peer-to-Peer Systems |
Authors: | Chen-Yu Tsai 蔡鎮宇 |
Advisor: | 周承復 |
Keyword: | 端對端,網路電視,雲端運算,成本最小化, Peer-to-peer,IPTV,Cloud computing,Cost minimization, |
Publication Year : | 2010 |
Degree: | 碩士 |
Abstract: | 隨著科技日新月異,服務業者開始大量利用端對端網路電視(P2PIPTV)提供線上影音內容。由於端點的不穩定性,端點上載頻寬及分享效率的變動, 服務業者一般必須佈署專屬伺服器,或利用雲端服務供應足夠的串流頻寬。這篇論文觀察現行的頻寬計價方式,串流伺服器頻寬需求的變動,以及隨之而來的最佳化機會。利用雲端運算服務的公用運算(Utility Computing) 模式,這篇論文提出兩階段的最佳化方案– 成本最小化的長期規劃及網路流量工程的短期調整。實驗模擬結果顯示我們提出的方案在成本最小化及負載平衡兩方面皆有不錯的效果。這篇論文另外也討論讓這套系統更精確有效所需要的相關知識,以及實做的一些想法。 P2P-IPTV has become a widely used method of providing online content. P2P-IPTV providers typically have to provision adequate streaming capacity using dedicated servers or public cloud services, due to peer instability, peer upload bandwidth and sharing effectiveness fluctuations. This thesis explores the current bandwidth pricing models, observes the fluctuations in streaming server bandwidth demands, and the oppurtunities for optimization. Taking advantage of the utility computing model of cloud infrastructure, this thesis proposes a two stage optimization scheme – long term planning by cost minimization and short term adaptation by traffic engineering. Simulations show that our system is effective for both cost minimization and load balancing. The thesis also discusses the knowledge needed to increase the accuracy and effectiveness of the proposed system, and ideas leading to an implementation. |
URI: | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/47212 |
Fulltext Rights: | 有償授權 |
Appears in Collections: | 資訊網路與多媒體研究所 |
Files in This Item:
File | Size | Format | |
---|---|---|---|
ntu-99-1.pdf Restricted Access | 2.01 MB | Adobe PDF |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.