請用此 Handle URI 來引用此文件:
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/65184
完整後設資料紀錄
DC 欄位 | 值 | 語言 |
---|---|---|
dc.contributor.advisor | 郭大維(Tei-Wei Kuo) | |
dc.contributor.author | Wei-Hsu Chen | en |
dc.contributor.author | 陳煒栩 | zh_TW |
dc.date.accessioned | 2021-06-16T23:28:51Z | - |
dc.date.available | 2017-08-01 | |
dc.date.copyright | 2012-08-01 | |
dc.date.issued | 2012 | |
dc.date.submitted | 2012-07-30 | |
dc.identifier.citation | [1] Albert Greenberg, James Hamilton, David A. Maltz, and Parveen Patel. The cost of a cloud: research problems in data center networks. SIGCOMM Comput. Commun. Rev., 39(1):68–73, December 2008.
[2] Michael Armbrust, Armando Fox, Rean Griffith, Anthony D. Joseph, Randy H. Katz, Andrew Konwinski, Gunho Lee, David A. Patterson, Ariel Rabkin, Ion Stoica, and Matei Zaharia. Above the clouds: A berkeley view of cloud computing. Technical Report UCB/EECS-2009-28, EECS Department, University of California, Berkeley, Feb 2009. [3] The Green Grid. Green grid data center power efficiency metrics: Pue and dcie citebitex. Technical report, 2007. [4] Amazon EC2 Pricing. http://aws.amazon.com/ec2/pricing/. [5] John R. Douceur, Jeremy Elson, Jon Howell, , and Jacob R. Lorch. The utility coprocessor: Massively parallel computation from the coffee shop. In Proceedings of 2010 USENIX Annual Technical Conference, June 2010. [6] Ssh filesystem. http://fuse.sourceforge.net/sshfs.html. [7] Hongyi Wang, Qingfeng Jing, Rishan Chen, Bingsheng He, Zhengping Qian, and Lidong Zhou. Distributed systems meet economics: pricing in the cloud. In Proceedings of the 2nd USENIX conference on Hot topics in cloud computing, Hot- Cloud’10, pages 6–6, Berkeley, CA, USA, 2010. USENIX Association. [8] Profiling energy usage for efficient consumption. http://msdn.microsoft.com/en-us/library/dd393312.aspx. [9] Jonathan G. Koomey. Growth in data center electricity use 2005 to 2010. In Analytics Press, Atlanta, GA, 2011. [10] C. L. Liu and James W. Layland. Scheduling algorithms for multiprogramming in a hard-real-time environment. J. ACM, 20(1):46–61, January 1973. [11] K. Jansen. Parameterized approximation scheme for the multiple knapsack problem. In Proceedings of the Twentieth Annual ACM SIAM Symposium on Discrete Algorithms (SODA), 2009. [12] Hans Kellerer, Ulrich Pferschy, and David Pisinger. Knapsack Problems, Springer, 2004. [13] Gy‥orgy D’osa. The tight bound of first fit decreasing bin-packing algorithm is FFD(I)≤11/9 OPT(I)+6/9. In Combinatorics, Algorithms, Probabilistic and Experimental Methodologies, volume 4614 of Lecture Notes in Computer Science. Springer Berlin / Heidelberg, 2007. [14] James Hamilton. Cost of power in large-scale data centers. http://perspectives.mvdirona.com/. [15] Asit K. Mishra, Joseph L. Herrestein, Walfredo Cirne, and Chita R. Das. Towards characterizing cloud backend workloads: insights from google computing clusters. ACM SIGMETRICS Performance Evaluation Review, 37(4), March 2010. [16] Marcos Dias de Assuncao, Alexandre di Costanzo, and Rajkumar Buyya. Evaluating the cost-benefit of using cloud computing to extend the capacity of clusters. In Proceedings of the 18th ACM international symposium on High performance distributed computing, HPDC ’09, pages 141–150, New York, NY, USA, 2009. ACM. [17] AlexanderWieder, Pramod Bhatotia, Ansley Post, and Rodrigo Rodrigues. Conductor: Orchestrating the clouds. In Proceedings of the 4th Workshop on Large Scale Distributed Systems and Middleware (LADIS), Z‥urich, Switzerland, July 2010. [18] U. Sharma, P. Shenoy, S. Sahu, and A. Shaikh. A cost-aware elasticity provisioning system for the cloud. In Distributed Computing Systems (ICDCS), 2011 31st International Conference on, pages 559 –570, june 2011. [19] sourceforge. Fuse filesystem in userspace. http://fuse.sourceforge.net/. [20] Amazon AWS. Amazon simple storage service. http://aws.amazon.com/s3/. | |
dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/65184 | - |
dc.description.abstract | 許多企業或是組織在客戶急遽增加的時候,都會面臨擴增電腦設備(IT infrastructure)的問題。建立一個新的資料中心(data center)需要花費龐大的資金,而且不彈性的資源使用方式是非常不符合經濟效益的。 近年來許多公司已經將雲端計算(cloud computing)當作是部分的替代方案,但是很多公司原本就擁有了自己的計算設備,因此這些近端叢集和遠端雲端計算形成了一個混合雲系統(hybrid cloud system)。近端叢集有著很短的延遲(latency),但是資源有限,而遠端雲端計算雖然有很長的延遲,但卻有著無限的資源。如何能夠結合雲端運算跟既有的近端叢集來讓系統的效能增加並且符合成本效益,變成了一個重要的議題。在此篇研究中,我們設計了混合雲系統,可以讓企業公司在既有的近端叢集上跟遠端雲端上執行使用者的應用程式。此系統有一個資料庫,保存了應用程式的許多資料,讓分派者(dispatcher)可以根據此資料來排成工作到近端叢集或是遠端雲端。使用者可以對自己的應用程式設定期限(deadline)的需求,分派者將會安排出工作時程(schedule)來滿足期限的限制。此外,站在公司企業的觀點,混合雲系統會將執行工作所需的花費降到最低。我們在亞馬遜雲端服務(Amazon Web Services)上面實驗混合雲系統,並且利用合理的成本得到大量的效能提升。 | zh_TW |
dc.description.abstract | Many enterprises or organizations face the problems to augment their IT infrastructure to serve fast growing clients. It takes huge cost to build up a new data center and the non-elasticity of resources makes it very cost-inefficient. Recent years, these companies follow to use cloud computing as parts of solutions; however, many of the companies already have existing computing infrastructure, and thus the local clusters and the remote cloud form a hybrid cloud system. The local cluster has short latency but limited resources, while the remote cloud computing has long latency but with unlimited resources. How to leverage the cloud computing with existing local clusters to improve performance cost-effectively becomes an important issue. In this work, we design a hybrid cloud system that enables the enterprises to run the users' applications on both existing local clusters and the remote cloud. The system maintains a database that records necessary information about applications, and the dispatcher schedules tasks to local clusters or to the remote cloud based on the database. The users can specify their deadline requirements for their application, and the dispatcher would derive a schedule to meet their deadline constraints. Moreover, in the perspective of enterprises, the hybrid cloud would minimize the total cost to execute their workloads. We evaluated the hybrid cloud system on the Amazon Web Services and our system gained great performance improvement with a reasonable total cost. | en |
dc.description.provenance | Made available in DSpace on 2021-06-16T23:28:51Z (GMT). No. of bitstreams: 1 ntu-101-R99922122-1.pdf: 797725 bytes, checksum: 0542086be17fd833ef3a2032d96d4847 (MD5) Previous issue date: 2012 | en |
dc.description.tableofcontents | List of Figures x
List of Tables xi 1 Introduction 1 2 Problem Statement 4 2.1 Challenges 4 2.2 Goals 5 3 System Overview 7 4 Task Selection and Scheduling Protocols 9 4.1 Overview 9 4.2 System Model and Problem Definition 9 4.3 Cost-Minimization Protocol 12 4.4 Implementation Remarks for Special Timing Constraints 15 5 Evaluation 19 5.1 Methodology 19 5.2 Experiment Results 21 6 RelatedWork 28 7 Conclusion 30 Bibliography 32 | |
dc.language.iso | en | |
dc.title | 混合雲之工作分派 | zh_TW |
dc.title | Task Dispatch of Hybrid Cloud | en |
dc.type | Thesis | |
dc.date.schoolyear | 100-2 | |
dc.description.degree | 碩士 | |
dc.contributor.coadvisor | 蘇雅韻(Ya-Yunn Su) | |
dc.contributor.oralexamcommittee | 逄愛君(Ai-Chun Pang),薛智文(Chih-Wen Hsueh),修丕承(Pi-Cheng Hsiu) | |
dc.subject.keyword | 雲端計算,混合雲,成本,工作分派, | zh_TW |
dc.subject.keyword | cloud computing,hybrid cloud,cost,dispatch, | en |
dc.relation.page | 34 | |
dc.rights.note | 有償授權 | |
dc.date.accepted | 2012-07-31 | |
dc.contributor.author-college | 電機資訊學院 | zh_TW |
dc.contributor.author-dept | 資訊工程學研究所 | zh_TW |
顯示於系所單位: | 資訊工程學系 |
文件中的檔案:
檔案 | 大小 | 格式 | |
---|---|---|---|
ntu-101-1.pdf 目前未授權公開取用 | 779.03 kB | Adobe PDF |
系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。