高綠能雲端資源管理系統

近年來，雲端運算已成為新興的網路議題，其中IaaS (Infrastructure as a Service)的服務也日漸盛行。在IaaS中，雲端資源管理系統負責管理資源的配置，而不同的資源排程及配置會導致實際的電能消耗、資源使用率及實體機器負載的不同，因此，如何設計雲端資源管理系統是一個重要的議題。在過去的研究中，許多學者已提出各種雲端資源配置法，來提昇雲端系統的效能，節省能源或提高使用者服務品質。然而，雲端服務需兼顧系統廠商與顧客的滿意度，因此，如何讓雲端資源管理能提供如此的彈性就成為一個有趣的議題。在本篇論文中，我們提出了一個雲端服務的MaxFit配置演算法，使系統管理者可以在進行資源的配置及排程時兼顧使用者滿意度及節能，並進行動態搬移來增進系統效能。我們針對不同的使用者滿意度及節能偏好來檢測所提出的方法，結果顯示與偏重使用者滿意度及偏重節能的資源配置法相比較，MaxFit可根據系統偏好達到彈性配置及調整，並可同時考量使用者滿意度及節能。

關鍵字

資源管理；雲端；節能；使用者滿意度；虛擬機器；資源配置；資源排程

並列摘要

In recent years, cloud computing has become a popular research subject. In the IaaS (Infrastructure as a Service), the cloud resource management system is responsible for managing and allocating resources and different resource scheduling and allocation scheme will lead to different energy consumption, resource utilization and user satisfaction. Thus, how to design an efficient resource management system is an important issue. In the past studies, many researchers have proposed a variety of cloud resource allocation schemes to improve the performance, energy saving or user satisfaction of a cloud system. However, cloud services need to consider both vendor and user satisfaction, and thus how to manage the cloud resource to provide such flexibility has become an interesting issue. In this thesis, we propose a cloud resource allocation algorithm called MaxFit to allow a system administrator to manage resources taking into account user satisfaction and energy-saving. Simulation results show that, along with on-line Virtual Machine migration, comparing with the other algorithm that either emphasis on user satisfaction or energy-saving, MaxFit achieves better flexibility to meet administrators’ preferences, and performs well in various system parameter settings.

並列關鍵字

energy-saving ； user satisfaction ； VM ； resource allocation ； resource scheduling ； resource management ； Cloud

參考文獻

[4] B. Sotomayor, et al. , “Virtual Infrastructure Management in Private and Hybrid Clouds,” in Internet Computing, IEEE, Vol. 13, pp 14 - 22, 2009.

[5] B.P. Rimal, et al., “A Taxonomy and Survey of Cloud Computing Systems,” in 2009 Fifth International Joint Conference on INC, IMS and IDC, pp 44 – 51, 2009.

[6] Hsu Mon Kyi and Thinn Thu Naing, “An Efficient Approach for Virtual Machines Scheduling on A Private Cloud Environment,” in 2011 4th International conference on Broadband Network and Multimedia Technology, IEEE, pp. 365-369, 2011.

[7] Jinhua Hu, et al., “A Scheduling Strategy on Load Balancing of Virtual Machine Resources in Cloud Computing Environment,” in 2010 3rd International Symposium on Parallel Architectures, Algorithms and Programing, IEEE, pp. 89-96, 2010.

[8] Yuan Yuan and Wen-Cai Liu, “Efficient Resource Management for Cloud Computing,” in 2011 international conference on ICSEM, IEEE, pp. 233-236, 2011.

國際替代計量

高綠能雲端資源管理系統

全文下載

主題瀏覽