雲端基礎設施服務中以服務品質協議為基礎之資源分配策略

SLA-Based Resource Allocation Policies for Infrastructure as a Service Provider (IaaS) in Clouds

沈孟助(Meng-Chu Shen)

指導教授 ： 廖文華

大同大學/經營設計學院/資訊經營學系所/碩士(2012年)

摘要

雲端軟體服務供應商(SaaS)藉由網際網路提供使用者大量的應用程式，為滿足硬體資源的需求SaaS供應商通常向IaaS供應商租用硬體資源。當SaaS供應商向IaaS供應商提出需求時，IaaS供應商會先確認是否有足夠的資源以滿足雙方簽訂的服務品質協議(SLA)。在以往的文獻中通常IaaS只簡單的計算可用資源即做出決定。然而本論文針對IaaS供應商提出了以服務品質協議為基礎之資源分配策略。我們不但確認了可用資源同時也採用了三種資源分配演算法來協助做決策。我們所採用的三種資源分配策略分別為：啟用新的實體機或虛擬機、虛擬機即時遷移以及虛擬機刪除，這些方案透過成本的評估以幫助IaaS決定是否接受SaaS所提出的需求。經由實驗結果顯示，我們所提出的演算法可以顯著的利潤。

關鍵字

服務品質協議(SLA) ； 雲端基礎設施服務(IaaS) ； 存取控制

並列摘要

Software as a Service (SaaS) provides applications for end users using the Internet and typically leases resources from the Infrastructure as a Service (IaaS). When SaaS requests are submitted to the IaaS, the IaaS determines whether there are sufficient resources to satisfy the service level agreement (SLA) between the SaaS and IaaS. Previous studies have only calculated the available resources to make decisions. This study proposes an SLA-based admission control for the IaaS. This method not only determines available resources but also uses three resource-allocation algorithms to perform decision-making. Our three resource allocation algorithms include initiating physical machine or virtual machine, migration, and deletion. These schemes evaluate cost to determine whether to accept an SaaS request. Simulation results showed that the proposed algorithm can provide significant benefits.

並列關鍵字

Infrastructure as a Service (IaaS) ； cloud computing ； Admission control ； service level agrenment (SLA)

參考文獻

[1]A. Andrzejak, D. Kondo, and S. Yi, “Decision Model for Cloud Computing under SLA Constraints,” IEEE International Symposium on Modeling, Analysis & Simulation of Computer and Telecommunication Systems (MASCOTS), 2011.

[2]D. Breitgand, G. Kutiel, and D. Raz, “Cost-Aware Live Migration of Services in the Cloud,” ACM 3rd Annual Haifa Experimental Systems Conference, 2010.

[3]R. Buyya, C.-S. Yeo, S. Venugopal, J. Broberg, and I. Brandic, “Cloud Computing and Emerging IT Platforms: Vision, Hype, and Reality for Delivering Computing as the 5th Utility,” ACM Future Generation Computer Systems, Vol. 25, No. 6, pp. 599-616, June, 2009.

[6]V.C. Emeakarohaa, M.A.S. Netto, R.N. Calheiros, I. Brandic, R. Buyya, and C.A.F.D. Rose, “Towards autonomic detection of SLA violations in Cloud infrastructures,” Journal Future Generation Computer Systems, Vol. 28, Issue 7, pp.1017-1029, 2012.

[7]H. Goudarzi and M. Pedram, “Multi-dimensional SLA-based Resource Allocation for Multi-tier Cloud Computing Systems,” IEEE International Conference on Cloud Computing (CLOUD), 2011.