Multi-objective Optimization of Grid Computing for Performance, Energy and Cost

Abstract = 0 times | WORD = 25 times


Ahmed Badri Muslim Fanfakhri Ali Yakoob Yousif Esraa Alwan


In this paper, new multi-objective optimization algorithm is proposed. It optimizes the execution time, the energy consumption and the cost of booked nodes in the grid architecture at the same time. The proposed algorithm selects the best frequencies depends on a new optimization function that optimized these three objectives, while giving equivalent trade-off for each one. Dynamic voltage and frequency scaling (DVFS) is used to reduce the energy consumption of the message passing parallel iterative method executed over grid. DVFS is also reduced the computing power of each processor executing the parallel applications. Therefore, the performance of these applications is decreased and so on the payed cost for the booking nodes is increased.  However, the proposed multi-objective algorithm gives the minimum energy consumption and minimum cost with maximum performance at the same time. The proposed algorithm is evaluated on the SimGrid/SMPI simulator while running the parallel iterative Jacobi method. The experiments show that it reduces on average the energy consumption by up to 19.7 %, while limiting the performance and cost degradations to 3.2 % and 5.2 % respectively.


Multi-objective optimization, Grid computing, Parallel message passing iterative applications and DVFS.


[1] GridPP, Distributed Computing for Data-intensive Research, Online available:
[2] Amazon Elastic Compute Cloud ,Online available:
[3] V. W. Freeh, F. Pan, N. Kappiah, D. K. Lowenthal, and R. Springer, “Exploring the energy-time tradeoff in MPI programs on a power-scalable cluster,” in Proceedings of the 19th IEEE International Parallel and Distributed Processing Symposium (IPDPS’05) - Papers – Volume 01, ser. IPDPS ’05. Washington, DC, USA: IEEE Computer Society, 2005, pp. 4a–4a.
[4] N. B. Rizvandi, J. Taheri, and A. Y. Zomaya, Some observations on optimal frequency selection in DVFS-based energy consumption minimization, J. Parallel Distrib. Comput., vol. 71, no. 8, pp. 1154–1164, Aug. 2011.
[5] Jean-Claude Charr, Rapha¨el Couturier, Ahmed Fanfakh, Arnaud Giersch. Dynamic Frequency Scaling for Energy Consumption Reduction in Synchronous Distributed Applications. ISPA 2014: The 12th IEEE International Symposium on Parallel and Distributed Processing with Applications, pp. 225-230. IEEE Computer Society, Milan, Italy, 2014.
[6] Jean-Claude Charr, Rapha¨el Couturier, Ahmed Fanfakh, Arnaud Giersch. Energy Consumption Reduction with DVFS for Message Passing Iterative Applications on Heterogeneous Architectures. The 16th IEEE International Workshop on Parallel and Distributed Scientific and Engineering Computing. pp. 922-931. IEEE Computer Society, INDIA, 2015.
[7] Ahmed Fanfakh, Jean-Claude Charr, Raphael Couturier, Arnaud Giersch. Optimizing the energy consumption of message passing applications with iterations executed over grids. Journal of Computational Science, 2016.
[8] T. Rauber and G. Rünger, Analytical modeling and simulation of the energy consumption of independent tasks, in Proceedings of the Winter Simulation Conference, ser. WSC ’12. Winter Simulation Conference, 2012, pp. 245:1–245:13.
[9] Jiang, J., Lin, Y., Xie, G., Fu, L., Yang, J.: Time and energy optimization algorithms for the static scheduling of multiple workflows in heterogeneous computing system. Journal of Grid Computing 1–22, 2017.
[10] Ke Liu, Hai Jin, Jinjun Chen, Xiao Liu, Dong Yuan, Yun Yang, A Compromised-Time-Cost Scheduling Algorithm in SwinDeW-C for Instance-Intensive Cost-Constrained Workflows on a Cloud Computing Platform,The International Journal of High Performance Computing Applications,445-456, 2010.
[11] L. Zuo, L. Shu, S. Dong, C. Zhu and T. Hara, A Multi-Objective Optimization Scheduling Method Based on the Ant Colony Algorithm in Cloud Computing, in IEEE Access, vol. 3, no. , pp. 2687-2699, 2015.
[12] Amandeep Verma, Sakshi Kaushal, A hybrid multi-objective Particle Swarm Optimization for scientific workflow scheduling, Journal of Parallel Computing, Volume 62, Pages 1-19, 2017.
[13] Sonia Yassa, Rachid Chelouah, Hubert Kadima, and Bertrand Granado, Multi-Objective Approach for Energy-Aware Workflow Scheduling in Cloud Computing Environments, The Scientific World Journal, vol. 2013, Article ID 350934, 13 pages, 2013.
[14] E. Le Sueur and G. Heiser, Dynamic voltage and frequency scaling: The laws of diminishing returns, in proceedings of the 2010 Workshop on Power Aware Computing and Systems (HotPower’10), Oct. 2010.
[15] H. Casanova, A. Giersch, A. Legrand, M. Quinson, and F. Suter, Versatile, scalable, and accurate simulation of distributed applications and platforms,” Journal of Parallel and Distributed Computing, vol. 74, no. 10, pp. 2899–2917, Oct. 2014.
[16] J. Burgerscentrum, Iterative solution methods, Applied Numerical Mathematics, 51(4): 437-450, 2011.