Research on the Load Balancing Algorithm Based on the Datacenters Service

Abstract:

With the rapid development of cloud computing, the datacenters are widely used in various areas. Connected by optical fiber, the datacenters are always distributed unbalanced, as the service requirements are very different in different regions. To ensure each datacenter’s stable operation and make them share the equal amounts of risk, the service resources need to be distributed to distinct datacenters proportionately. Considering the service recourses of datacenters, this paper is aimed at proposing a dynamic load balancing algorithm. The algorithm, named Average Variance, can help the new tasks to be distributed with a dynamic adjustment on the basis of the current datacenter’s situation in real-time. And in this way, it can achieve the minimum average variance among datacenter’s occupation of service resource. The simulation results demonstrate that the Average Variance has a better performance than the Round Robin. Furthermore, the main consideration of the node in this paper is the utilization in each CPU.

• Periodical: Advanced Materials Research (Volumes 546-547)
• Pages: 420-425
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.546-547.420
• Online since: July 2012
• Authors: Rui Ying He, Yong Li Zhao, Wei Wang, Xin Su, Xin Yu Zhang
• Keywords: Datacenters, Dynamic Algorithm, Load Balance, Variance

References

[1] F.F. River: Minimizing the Load Redistribution Cost in Cluster Architectures (2004), in press.

[2] B. Yagoubi, Y. Slimani, in: Dynamic Load Balancing Strategy For Grid Computing. Proceedings of WASET, Vol. 13, page no 260-265 (2006).

[3] W. C. Frederico Abraham, Renato Cerqueira, Joao Luiz Campos, in: A Load-Balancing Strategy for Sort-First Distributed Rendering, in Proceedings of the Computer Graphics and Image Processing, Brazilian 2004, p.292 – 299.

DOI: 10.1109/sibgra.2004.1352973

[4] G. Henkelman, G. Johannesson and H. Jónsson, in: Theoretical Methods in Condencsed Phase Chemistry, edited by S.D. Schwartz, volume 5 of Progress in Theoretical Chemistry and Physics, chapter, 10, Kluwer Academic Publishers (2000).

[4] C. Mueller, "The sort-first rendering architecture for high performance graphics, in: in Proceedings of the 1995 symposium on Interactive 3D graphics, Monterey, California, United States, p.75 – ff (1995).

DOI: 10.1145/199404.199417

[5] Chang Hui, Lei Xiaoyong, Dai Shuling, in: A Dynamic Load Balancing Algorithm for Sort-first Rendering Clusters, IEEE Network (2007).

DOI: 10.1109/iccsit.2009.5234831

[6] Shen Binghu, Jin Zhefan, Pan Ruifang, in: Load balancing method based on render history in cluster rendering, Computer Application, vol. 26, pp.2843-2847 (2006).

[7] Yu Lei, Lin Zong-Kai, Guo Yu-Chai , Lin Shuo-Xun, in: Load balancing and fault-tolerant services in multi-server system, Journal of System Simulation, 2001, 13(3): 325~328(in Chinese).

[8] Rajkumar Buyya. High, in: Performance Cluster Computing: Architectures and Systems [M] , Prentice Hall PTR, NJ, USA, 1999. 226~310.