雲端運算的興起，不僅帶給人們在生活上極大的便利與享受，也掀起全新的商業模式。但所謂的雲端運算並不是全新的技術，而是一種概念上的創新與變革。它將傳統的計算資源、網路資源、以及儲存資源及其相關應用以網際網路服務的形式提供給終端使用者使用，並以公用計算的方式來提供計價收費。各大雲端廠商近年所關心的目標就是在提供便利服務的同時，還要妥善的利用系統資源，如此才能在提供經濟效益以及系統效能上做較佳的權衡。
本研究延續中央大學資工系在2012年利用虛擬化技術與虛擬機中介管理機制所打造了一個非商業性的雲端資訊安全實驗平台SAMEVED (System Architecture for Managing and Establishing Virtual Elastic Datacenters) 。SAMEVED除了可以讓終端使用者享受一般公有雲(Public Cloud)的虛擬機器(Virtual Machines)所提供的服務以外，使用者亦可以按照自行的發展需求來建置自己的虛擬資料機房(Virtual Elastic Datacenters)，來進行像是學校的網路安全課程等相關研究教學。在本研究中，我們修改並結合了開源雲端系統OpenStack並稱之為”SAMEVEDStack”，然後建立虛擬資料中心的資源配置機制來達到負載平衡，以改善以往當多個終端使用者使用本系統服務時所造成的系統效能下降瓶頸，以期可以提供更彈性的服務給終端使用者。我們將所提出的資源配置機制跟雲端系統最常見的三種資源配置機制相比較，發現本研究所提出的機制具有最好的效能。

Cloud computing is not a brand new technology but rather a kind of conceptual innovation and change. Cloud computing integrates conventional computing resources, network resources, storage resources and related software systems into internet services, typically in a “pay-as-you-go” manner. However, it has become a common concern for the cloud service providers to balance resource usage and system performance. That is, consolidating computing tasks to a smaller set of working machines usually implies less operational expense (such as power consumption) for the cloud service providers. Meanwhile, it also may increase the workload of the set of the working machines and consequently decrease the performance of the whole system. For a cloud platform of limited resources that faces a peak workload, it is critical to use a good resource allocation strategy to achieve better load balance that yields better system performance. This thesis presents a resource allocation strategy, which is implemented on a new cloud platform, namely “SAMEVEDStack.” The concept of SAMEVEDStack is derived from a platform, “SAMEVED” (System Architecture for Managing and Establishing Virtual Elastic Datacenters), which is developed by the Department of Computer Science and Information Engineering, National Central University, Taiwan. The SAMEVEDStack is a non-commercial experimental cloud platform. It is implemented on the architecture of OpenStack, and designed for conducting on-line network and computer security experiments. The experimental results show that, the proposed resource allocation strategy outperforms three prior popular resource allocation strategies on our SAMEVEDStack cloud platform.

摘要 i
Abstract ii
目錄 iii
圖目錄 v
表目錄 vi
第一章 緒論 1
前言 1
1-1 問題定義與實作目標 2
1-2 論文主要貢獻 4
1-3 論文架構 5
第二章 相關研究 6
2-1 相關系統工具 6
2-1-1 SAMEVED 6
2-1-2 OpenStack 8
2-1-3 Amazon Elastic Load Balancer 11
2-1-4 CloudStack 12
2-2 相關負載平衡策略 13
2-2-1 Statistic-based VM Placement Load balance Strategy 13
2-2-2 Dynamic-Migration-based Load Balance Strategy 14
第三章 系統設計 17
3-1 系統使用情境 17
3-2 系統架構模型 18
3-2-1 SAMEVED Frontend 23
3-2-2 SAMEVED Compute Controller 24
3-2-3 SAMEVED ComputeNode 27
3-2-4 SAMEVED Network Controller 28
3-2-5 SAMEVED Storage Controller 30
3-2-6 SAMEVED Watch 31
3-3 系統實作流程 34
3-3-1 系統硬體需求 34
3-3-2 系統軟體需求 36
3-4 系統運作細節 38
3-5 系統資源調度策略 41
第四章 實驗環境與測量 44
4-1 實驗環境背景 44
4-2 實驗環境假設 44
4-3 實驗運行結果 46
第五章 結論 49
第六章 未來研究方向 50
自動化計算(Auto Computing) 50
參考文獻 51

[1] M. Armbrust, A. Fox, R. Griffith, A. D. Joseph, R. Katz, A. Konwinski, G. Lee, D. Patterson, A. Rabkin, I. Stoica, and M. Zaharia, “Above the Clouds: A Berkeley View of Cloud Computing,” Commun Acm, vol. 53, no. 4, pp. 50–58, Apr. 2010.
[2] I. Foster, Y. Zhao, I. Raicu, and S. Lu, “Cloud Computing and Grid Computing 360-Degree Compared,” in Grid Computing Environments Workshop, 2008. GCE ’08, 2008, pp. 1–10.
[3] B. Furht, “Handbook of Cloud Computing,” in Handbook of Cloud Computing, B. Furht and A. Escalante, Eds. Boston, MA: Springer US, 2010, pp. 3–19.
[4] P. Mell and T. Grance, “The NIST Definition of Cloud Computing.”
[5] “Amazon Elastic Compute Cloud (Amazon EC2), Cloud Computing Servers.” [Online]. Available: http://aws.amazon.com/ec2/.
[6] “Google App Engine.” [Online]. Available: https://developers.google.com/appengine/?hl=zh-tw.
[7] “Windows Azure.” [Online]. Available: http://www.windowsazure.com/zh-tw/.
[8] “The Xen Project.” [Online]. Available: http://www.xenproject.org/.
[9] D. Chisnall, The definitive guide to the Xen hypervisor. Upper Saddle River, NJ: Prentice Hall, 2008.
[10] P. Barham, B. Dragovic, K. Fraser, S. Hand, T. Harris, A. Ho, R. Neugebauer, I. Pratt, and A. Warfield, “Xen and the art of virtualization,” Acm Sigops Oper. Syst. Rev., vol. 37, no. 5, pp. 164–177, 2003.
[11] D. E. Williams and Garcia, Virtualization with Xen including XenEnterprise, XenServer, and XenExpress. Burlington, MA: Syngress, 2007.
[12] “KVM.” [Online]. Available: http://www.linux-kvm.org/page/Main_Page.
[13] “VMware.” [Online]. Available: http://www.vmware.com/tw.
[14] S. J. Chen, J. Y. Huang, C. T. Huang, and W. J. Wang, “SAMEVED: A System Architecture for Managing and Establishing Virtual Elastic Datacenter,” Int. J. Grid High Perform. Comput.
[15] “Citrix XenServer.” [Online]. Available: http://www.citrix.com.tw/products/XenServer/overview.html.
[16] “Credit Scheduler - Xen.” [Online]. Available: http://wiki.xen.org/wiki/Credit_Scheduler.
[17] “ApacheTM Hadoop®!” [Online]. Available: http://hadoop.apache.org/.
[18] “OpenStack.” [Online]. Available: http://www.openstack.org/.
[19] M. Bist, M. Wariya, and A. Agarwal, “Comparing delta, open stack and Xen Cloud Platforms: A survey on open source IaaS,” in Advance Computing Conference (IACC), 2013 IEEE 3rd International, 2013, pp. 96–100.
[20] “Ceilometer.” [Online]. Available: https://wiki.openstack.org/wiki/Ceilometer.
[21] “OpenFoundry.” [Online]. Available: http://www.openfoundry.org/of/.
[22] “Free source code hosting for Git and Mercurial by Bitbucket.” [Online]. Available: https://bitbucket.org/.
[23] “GitHub • Build software better, together.” [Online]. Available: https://github.com/.
[24] “Amazon Elastic Block Store (EBS) – Persistent Storage.” [Online]. Available: http://aws.amazon.com/ebs/.
[25] “Amazon S3, Cloud Computing Storage for Files, Images, Videos.” [Online]. Available: http://aws.amazon.com/s3/.
[26] “Amazon Elastic Load Balancing.” [Online]. Available: http://aws.amazon.com/elasticloadbalancing/.
[27] “Amazon Virtual Private Cloud.” [Online]. Available: http://aws.amazon.com/vpc/.
[28] “Apache CloudStack.” [Online]. Available: http://cloudstack.apache.org/.
[29] Z. Zhang, L. Xiao, Y. Li, and L. Ruan, “A VM-based Resource Management Method Using Statistics,” in 2012 IEEE 18th International Conference on Parallel and Distributed Systems (ICPADS), 2012, pp. 788–793.
[30] Z. Zhang, H. Wang, L. Xiao, and L. Ruan, “A statistical based resource allocation scheme in cloud,” in 2011 International Conference on Cloud and Service Computing (CSC), 2011, pp. 266–273.
[31] H. Ren, Y. Lan, and C. Yin, “The load balancing algorithm in cloud computing environment,” in 2012 2nd International Conference on Computer Science and Network Technology (ICCSNT), 2012, pp. 925–928.
[32] “Open Source Private and Hybrid Clouds from Eucalyptus | Open Source. AWS-compatible. Private Clouds.” [Online]. Available: http://www.eucalyptus.com/.
[33] F. Wuhib, R. Stadler, and H. Lindgren, “Dynamic resource allocation with management objectives - Implementation for an OpenStack cloud,” in Network and service management (cnsm), 2012 8th international conference and 2012 workshop on systems virtualiztion management (svm), 2012, pp. 309–315.