臺灣博碩士論文加值系統

在雲端計算平台(Cloud Platform, CP)的經營模式下，伺服器群的資源部署，是以雲端客戶們之需求規劃以及搭配必要的後勤系統方式來設計。運作中的伺服器群必須全天候服務，機器故障顯然無法避免。為了提高雲端平台的系統容錯性能，備份伺服器的概念是一個有效可行之策略。
方法: 本研究論文針對雲端計算的後勤系統架構，採用排隊理論中之「有限源排隊模型 (Finite Source Queue, FSQ)」，搭配兩層備援伺服器架構，作為設計之核心重點。原則上，雲端計算平台隨時皆要維持固定數量伺服器(Online Servers)對外穩定提供服務品質，但是當有任何一個線上伺服器故障時，本系統就會提供一個暖熱機之備援伺服器(Warm-standby Server)，轉為線上伺服器，隨時確保雲端計算平台，對外保有定量之線上伺服器的服務品質；同時，系統內之一個冷機備援伺服器(Cold-standby Server)就會轉為暖熱機之備援伺服器。
結果: 本研究論文主要之創意，在於將CP服勤的定量伺服器群視同於FSQ模型中的有限源(Finite Source)，此種新的設計模式，以有限源排隊理論為數理基礎，建構出雲端計算平台的後勤體系，同時推導相關數理方程式，建立系統必要性能函數，完成成本最佳化之計量研究；最後吾人也使用模擬工具驗證成本模式的可行性。
結論: 因此針對CP後勤體系，以經營成本最佳化為導向，本研究成果確實提供了一個有效可行的系統規劃，作為雲端計算企業經濟之參考。

On cloud platform, the computing resources are provided in an on-demand and dynamic fashion for the cloud customers via Internet. For improving system reliability and availability, the concept of fault tolerance is adopted to allow the cloud platform to maintain necessary quality of service even when some operational servers fail. The construction on the cloud logistics is mainly concerned with the deployment of standby servers. The goal of this research is to provide an effective decision support for cloud logistics to get around the selection on spares quantities in a haphazard way.

The proposed novel design pattern is developed for approaching optimal cost on logistics using the two-level standbys scheme from finite-source queuing theory. The detailed system flow diagram is provided to grasp the whole system profile. To formulate the proposed approach, the mathematical analysis on cost pattern has been made quantitatively in detail. Relevant simulations have also been conducted to validate the proposed optimization model. The design illustration is presented to demonstrate engineering application scenario in cloud environment, hence the proposed two-level standbys approach indeed provides a feasibly cost-oriented framework to meet logistic economy.

Abstract
Chapter 1 Introduction
Chapter 2 Related Work
2.1 Overview on Cloud Computing
2.2 Related Work
Chapter 3 Two-level Standbys Approach on Cloud Platform
3.1 The Proposed Two-level Logistic System on Cloud Platform
Chapter 4 Mathematical Analysis
4.1 Review of Basic Instaneous Process on Queuing Model
4.1.1 The arrival process
4.1.2 The service process
4.1.3 Difference equation for Pn(t)
4.2 Birth-and-Death Process on Queuing System
4.3 Mathematical Analysis using Recursive Approach
4.4 Mathematical Analysis using Birth-and-Death Approach
4.5 System Measure
4.6 Illustrative example with Computational Details
Chapter 5 Performance Evaluation
5.1 Introduction to MATLAB Simulation Tool
5.2 Cost Analysis
5.3 Optimization Evaluation
Chapter 6 Conclusion
Reference
Appendix A

[1]M. Armbrust M, A. Fox, R. Griffith et al., “A view of cloud computing,” Communications of ACM, vol. 53, no.4, pp.50–58, 2010.
[2]L. M. Vaquero, L. Rodero-Merino, J. Caceres, and M. Lindner, “A break in the clouds: Towards a cloud definition,” ACM SIGCOMM Computer Communication Review, vol. 39, no. 1. pp. 50–55, Dec. 2009.
[3]S. K. Garg, S. Versteeg and R. Buyya, "A framework for ranking cloud computing services," Future Generation Computer Systems, 29 (2013), 1012–1023.
[4]S. Marston and Z. Li, “Cloud computing –The business perspective,” Decision Support Systems, 51(2011), 176–189.
[5]D. Durkee, “Why cloud computing will never be free,” Communications of the ACM, vol.53, no. 5, pp.62-69, 2010.
[6]Jula, E. Sundararajan and Z. Othman, "Cloud computing service composition: A systematic literature review," Expert Systems with Applications, vol. 41, pp. 3809–3824, 2014.
[7]R. B. Cooper (1981). Introduction to Queuing theory, 2nd edition, Elsevier Science Publishing Co., Inc. 52 Vanderbilt Avenue, New York 10017.
[8]D. Gross, J. F. Shortle, J. M. Thompson and C. M. Harris (2008). Fundamentals of Queuing Theory (Fourth edition), A John Wiley &Sons, Inc., New York.
[9]Peter Mell and Tim Grance, “The NIST definition of cloud computing”, Special Publication 800-145 Sep, 2011.
[10]P. Patel, A. Ranabahu, and A. Sheth, Service level agreement in cloud computing. In Proceeding of the 24th ACM SIGPLAN Conference Companion on Object Oriented Programming System Languages and Applications (OOPSLA’09).
[11]J. Lejeune, L. Arantes, J. Sopena, and P. Sens, “Service Level Agreement for Distributed Mutual Exclusion in Cloud Computing,” In Proceedings of 2012 12th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing, pp. 180-187.
[12]Available at http://en.wikipedia.org/wiki/Service_level_agreement
[13]K. Xiong K and H. Perros, Service performance and analysis in cloud computing. In Proceedings of IEEE World Conference Services, 2009, pp 693–700.
[14]Y.-K. Lin and P.-C. Chang, “Maintenance reliability estimation for a cloud computing network with nodes failure,” Expert Systems with Applications, 38 (2011), 14185–14189.
[15]H. Khazaei, J. Misic, and V.B. Misic, “Performance analysis of cloud computing centers using M/G/m/m+r queuing systems,” IEEE Transactions on Parallel and Distributed Systems, vol.23, no. 5, pp. 936–943, 2012.
[16]B. Hu, Y. Sudo, K. Hato, Y. Murata and J. Murayama, “Cost reduction evaluation of sharing backup servers in inter-cloud,” 19th Asia-Pacific Conference on Communications (APCC), Bali, Indonesia, 2013, pp.256–261.
[17]F.-C. Jiang, C.-T. Yang, Y.-H. Chen, W.-T. Huang and H.-Y. Chao, “Decision Support for Cloud Logistics by Optimizing the Quantities of Standby Servers in Cloud Environment,” In Proceeding of 2015 International Conference on Cloud Computing and Big Data (CCBD 2015), pp. 169-172.
[18]Available at https://en.wikipedia.org/wiki/Birth%E2%80%93death_process
[19]MATLAB website: http://www.mathworks.com/products/matlab/
[20]MATLAB wiki: https://en.wikipedia.org/wiki/MATLAB
[21]MATLAB 程式設計與應用 http://www.cs.nthu.edu.tw/~jang/mlbook/ch1/