An Energy-Aware Optimization Model Based on Data Placement and Task Scheduling

Recently, technologies on reducing energy consumption of data centers have drawn considerable attentions. One constructive way is to improve energy efficiency of servers. Aiming at this goal, we propose a new energy-aware optimization model based on the combination of data placement and task scheduling in this paper. The main contributions are: (1)The impact of servers' performance on energy consumption is explored. (2) The model guarantees 100% data locality to save network bandwidth. (3) As tasks involved in cloud computing are usually tens of thousands, in order to solve this large scale optimization model efficiently, specific-design encoding and decoding methods are introduced. Based on these, an effective evolutionary algorithm is proposed. Finally, numerical experiments are made and the results indicate the effectiveness of the proposed algorithm.

[1]  Heinrich von Stackelberg,et al.  Stackelberg (Heinrich von) - The Theory of the Market Economy, translated from the German and with an introduction by Alan T. PEACOCK. , 1953 .

[2]  Hong Liu,et al.  Energy proportional datacenter networks , 2010, ISCA.

[3]  Luiz André Barroso,et al.  The Case for Energy-Proportional Computing , 2007, Computer.

[4]  Flavien Quesnel,et al.  Cooperative and reactive scheduling in large‐scale virtualized platforms with DVMS , 2013, Concurr. Comput. Pract. Exp..

[5]  Robert G. Jeroslow,et al.  The polynomial hierarchy and a simple model for competitive analysis , 1985, Math. Program..

[6]  Feng Zhao,et al.  Energy aware consolidation for cloud computing , 2008, CLUSTER 2008.

[7]  Sanjay Ghemawat,et al.  MapReduce: Simplified Data Processing on Large Clusters , 2004, OSDI.

[8]  Yonggang Wen,et al.  An Empirical Investigation of the Impact of Server Virtualization on Energy Efficiency for Green Data Center , 2013, Comput. J..

[9]  J. Bard.  Some properties of the bilevel programming problem , 1991 .

[10]  Michelle Sibilla,et al.  Systems and Virtualization Management. Standards and the Cloud - Third International DMTF Academic Alliance Workshop, SVM 2009, Wuhan, China, September 22-23, 2009. Revised Selected Papers , 2010, Communications in Computer and Information Science.

[11]  Yuping Wang,et al.  An evolutionary algorithm for solving nonlinear bilevel programming based on a new constraint-handling scheme , 2005, IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews).

[12]  Tom White,et al.  Hadoop: The Definitive Guide , 2009 .

[13]  Mark Carlson.  Systems and Virtualization Management : Standards and the Cloud (A report on SVM 2012) , 2013, Journal of Network and Systems Management.