因綠色運算與環境保護的提倡，運算中心耗能倍受重視，如何在不違反與使用者之間的服務層協議情況下，節省運算中心耗能為重要議題。虛擬機聯合將運算中心的工作集中並關閉沒有工作的伺服器，可以有效降低運算中心之耗能。然而將虛擬機集中會造成伺服器過載之情況發生，必須透過搬移虛擬機來達到負載平衡。過於頻繁的虛擬機搬移會造成運算中心效率損失，並且佔用運算中心的內部網路頻寬。本研究提出一個虛擬機資源使用量預測方法，根據虛擬機之歷史資源使用量預測其往後的資源需求，在預測成功時不搬移虛擬機以減少搬移次數，並於預測失敗時調整虛擬機配置，維護與使用者之協議。本研究提出伺服器狀態分群法，可縮短搬移虛擬機時的挑選目標伺服器之花費時間。本研究模擬實驗結果比較相關之研究方法，可減少13%~41%之虛擬機搬移次數，降低總協議違反量15%~50%，並節省耗能2%~3%。使用本研究提出的伺服器狀態分群法，運算中心花費於計算平衡負載之時間可減少67%。

Datacenter energy consumption is now considered a significant issue because green computing has drawn a lot of attentions. Virtualization technology improves efficiency of the resource utilization in large-scale datacenters. Dynamic consolidation of Virtual Machines (VMs) reduces energy consumption by VM live migration that not only optimizes the placement of VMs, but also switches idle nodes to sleep mode. However, consolidation might create more resource demand and lead to violate service level agreements (SLAs) between end users and cloud computing providers. The goal of this study is to meet the requirement of SLA and lower the energy consumption of datacenters. We propose a VM allocation policy that minimizes the number of active servers and reduce energy consumption of datacenters by estimating the resource requirements of VMs according to previous VM resource usage. The proposed policy moves a VM only when the resource demand of VM become out of expectation, so that unnecessary migrations are eliminated and SLA can be preserved. This study also presents a server status grouping policy, which shortens the duration for selecting migration destinations before allocation. Compared to the heuristics proposed in previous studies, the proposed policy reduced 13% to 41% of VM migration frequency, 15% to 50% of SLA violations, and 2% to 3% of energy consumption. The duration of the load balance can be reduced by a maximum of 67% by determining the server status grouping policy.

[1] Amazon EC2. Available from: http://aws.amazon.com/ec2/.
[2] L.A. Barroso and U. Holzle. The Case for Energy-Proportional Computing, IEEE Computer, Volume 40, pp. 33-37, 2007.
[3] A. Beloglazov, J. Abawajy, and R. Buyya, Energy-aware resource allocation heuristics for efficient management of datacenters for Cloud computing, Future Generation Computer Systems, Volume 28, Issue 5, pp. 755-768, 2011.
[4] A. Beloglazov and R. Buyya, Optimal Online Deterministic Algorithms and Adaptive Heuristics for Energy and Performance Efficient Dynamic Consolidation of Virtual Machines in Cloud Data Centers, Concurrency and Computation: Practice and Experience, ISSN: 1532-0626, Wiley Press, New York, USA, 2011, DOI: 10.1002/cpe.1867.
[5] R. Brown, et al., Report to Congress on Server and Data Center Energy Efficiency: Public Law 109-431, Lawrence Berkeley National Laboratory, 2007.
[6] R.N. Calheiros, R. Ranjan, A. Beloglazov, C.A.F.D. Rose, and R. Buyya, CloudSim: a toolkit for modeling and simulation of cloud computing environments and evaluation of resource provisioning algorithms, Software—Practice & Experience, Volume 41, Issue 1, pp. 23-50, 2011.
[7] C. Clark, et al. Live Migration of Virtual Machines, Proceedings of the 2nd conference on Symposium on Networked Systems Design and Implementation. pp. 273-286, 2005.
[8] E. Duesterwald, C. Cascaval, and S. Dwarkadas. Characterizing and Predicting Program Behavior and its Variability, Proceedings of 12th International Conference on Parallel Architectures and Compilation Techniques. pp. 220-231, 2003.
[9] T.V.T. Duy, Y. Sato, and Y. Inoguchi. Performance Evaluation of a Green Scheduling Algorithm for Energy Savings in Cloud Computing, IEEE International Symposium on Parallel & Distributed Processing, Workshops and Phd Forum (IPDPSW). pp. 1-8, 2010.

[10] T.V.T. Duy, Y. Sato, and Y. Inoguchi, A Prediction-Based Green Scheduler for Datacenters in Clouds, IEICE Transactions on Information and Systems, Volume E94-D, Issue 9, pp. 1731-1741, 2011.
[11] X. Fan, W.-D. Weber, and L.A. Barroso. Power Provisioning for a Warehouse-sized Computer, Proceedings of the 34th annual international symposium on Computer architecture. pp. 13-23, 2007.
[12] M. Gomez, D. Perales, and E.J. Torres. An Energy-Aware Design and Reporting Tool for On-Demand Service Infrastructures, the 10th IEEE/ACM International Conference on Grid Computing. pp. 209-216, 2009.
[13] R. Ge, et al., PowerPack: Energy Profiling and Analysis of High-Performance Systems and Applications, IEEE Transactions on Parallel and Distributed Systems, Volume 21, Issue 5, pp. 658-671, 2010.
[14] P. Graubner, M. Schmidt, and B. Freisleben. Energy-Efficient Management of Virtual Machines in Eucalyptus, IEEE International Conference on Cloud Computing (CLOUD). pp. 243-250, 2011.
[15] F. Hermenier, X. Lorca, J.-M. Menaud, G. Muller, and J. Lawall. Entropy: a consolidation manager for clusters, Proceedings of the ACM SIGPLAN/SIGOPS international conference on Virtual execution environments. pp. 41-50, 2009.
[16] Q. Huang, F. Gao, R. Wang, and Z. Qi. Power Consumption of Virtual Machine Live Migration in Clouds, the 3rd International Conference on Communications and Mobile Computing (CMC). pp. 122-125, 2011.
[17] A. Kivity, Y. Kamay, and D. Laor. kvm: the Linux Virtual Machine Monitor, In Proceedings of the Linux Symposium. pp. 225–230, 2007.
[18] D.E. Knuth, The Art of Computer Programming. Vol. 2, 2006.
[19] J.G. Koomey, Estimating total power consumption by servers in the US and the world, 2007. Available from: http://sites.amd.com/de/Documents/svrpwrusecom
pletefinal.pdf
[20] J.G. Koomey, Growth in data center electricity use 2005 to 2010, Analytics Press, 2011.

[21] A. Krioukov, et al. NapSAC: Design and Implementation of a Power-Proportional Web Cluster, ACM SIGCOMM Computer Communication Review. pp. 102-108, 2011.
[22] D. Kusic, J.O. Kephart, J.E. Hanson, and N. Kandasamy, Power and Performance Management of Virtualized Computing Environments Via Lookahead Control, Cluster Computing, Volume 12, Issue 1, pp. 1-15, 2009.
[23] A. Lenk, M. Klems, J. Nimis, S. Tai, and T. Sandholm. What's inside the Cloud? An architectural map of the Cloud landscape, Proceedings of the ICSE Workshop on Software Engineering Challenges of Cloud Computing. pp. 23-31, 2009.
[24] D. Nurmi, et al. The Eucalyptus Open-source Cloud-computing System, the 9th IEEE/ACM International Symposium on Cluster Computing and the Grid. pp. 124-131, 2009.
[25] K. Park and V.S. Pai. CoMon: A Mostly-Scalable Monitoring System for PlanetLab, ACM SIGOPS Operating Systems Review. pp. 65-74, 2006.
[26] J. Peng, et al. Comparison of Several Cloud Computing Platforms, the 2nd International Symposium on Information Science and Engineering (ISISE). pp. 23-27, 2009.
[27] M. Rosenblum and T. Garfinkel. Virtual machine monitors: current technology and future trends, IEEE Computer, Volume 38, pp. 39-47, 2005.
[28] H.N. Van, F.D. Tran, and J.-M. Menaud. Autonomic virtual resource management for service hosting platforms, Proceedings of the 2009 ICSE Workshop on Software Engineering Challenges of Cloud Computing. pp. 1-8, 2009.
[29] W. Voorsluys, J. Broberg, S. Venugopal, and Rajkumar. Cost of Virtual Machine Live Migration in Clouds: A Performance Evaluation, Proceedings of the 1st International Conference on Cloud Computing. pp. 254 - 265, 2009.
[30] H. Yu, D. Zheng, B.Y. Zhao, and W. Zheng. Understanding user behavior in large-scale video-on-demand systems, Proceedings of the 1st ACM SIGOPS/EuroSys European Conference on Computer Systems. pp. 333-344, 2006.