HLA Collaborative Simulation Oriented Virtual Machine Task Scheduling Strategy
Aim at the lack of embedded load balancing mechanism in HLA simulation system and the heterogeneity of resources in the network modeling and simulation platform, the study of the initial deployment of HLA simulation task is performed. At first, a unified description model of the federation is established based upon the repulsion and pull relationship between federates; And then, using the analysis of the unified description model, a first detect first combine based coarse combination algorithm is proposed; Taking full consideration of load balance and the late migration efficiency, a Huffman coding tree based fine-grained combination algorithm is put forwarded. Finally, cloud computing simulation platform—CloudSim is utilized to perform the simulation experiment, the result demonstrates that the algorithm improves the management efficiency, fault tolerance and QoS of the resource.
KeywordsHLA simulation initial deployment load balance Huffman coding CloudSim
Unable to display preview. Download preview PDF.
- 1.S.I.S.C. (SISC). IEEE Standard for Modeling and Simulation (M&S) High Level Architecture (HLA) Framework and Rules. IEEE Computer Society (September 2000)Google Scholar
- 2.Yang, J., Tan, G., Wang, R.: A survey of dynamic load balancing strategies for parallel and distributed computing. Acta Electronica Sinica 38(5), 1122–1130 (2011) (in Chinese)Google Scholar
- 3.Jiang, J., Zhang, M.X., et al.: Study on load balancing algorithms based on multiple resources. Acta Electronica Sinica 30(8), 1148–1152 (2002) (in Chinese)Google Scholar
- 4.Zheng, B.G.: Achieving High Performance on Extremely Large Parallel Machines: Performance Prediction and Load Balancing. UIUC, Urbana (2005)Google Scholar
- 5.EI Ajaltouni, E., Boukerche, A., Zhang, M.: An Efficient Dynamic Load Balancing Scheme for Distributed Simulations on a Grid Infrastructure. In: Proceedings of the 12th 2008 IEEE/ACM International Symposium on Distributed Simulation and Real-Time Applications, pp. 61–68. IEEE Computer Society (2008)Google Scholar
- 6.Boukerche, A., De Grande, R.E.: Dynamic Load Balancing Using Grid Services for HLA-Based Simulations on Large-Scale Distributed Systems. In: Proceedings of the 13th 2009 IEEE/ACM International Symposium on Distributed Simulation and Real-Time Applications, pp. 175–183. IEEE Computer Society (2009)Google Scholar
- 7.Zhang, Y., Li, B., et al.: Research on Virtualization-based Simulation Environment Dynamically Building Technology for Cloud Simulation. In: Proceedings of ISAI, pp. 1754–1769 (2010)Google Scholar
- 8.De Grande, R.E., Boukerche, A.: Self-Adaptive Dynamic Load Balancing for Large-Scale HLA-based Simulation. In: Proceedings of the 2010 IEEE/ACM International Symposium on Distributed Simulation and Real-Time Applications, pp. 14–21. IEEE Computer Society (2010)Google Scholar
- 9.De Grande, R.E., Boukerche, A.: Distributed Dynamic Balancing of Communication Load for Large-Scale HLA-based Simulations. In: Proceeding of the 14th 2010 IEEE/ISCC International Symposium on Computers and Communications, pp. 1109–1114. IEEE Computer Society (2010)Google Scholar
- 10.Park, G.L., Shirazi, B., Marquis, J., et al.: Decisive path scheduling: a new list scheduling method. In: Proceedings of the International Conference on Parallel Processing, Bloomington, pp. 472–480. IEEE (1997)Google Scholar
- 11.Houshmand, M., Soleymanpour, E., Salami, H., et al.: Efficient scheduling of task graphs to multiprocessors using a combination of modified simulated annealing and list based scheduling. In: Proceedings of the 3rd International Symposium on IITSI, Jinggangshan, pp. 350–354. IEEE (2010)Google Scholar