Evolutionary algorithm-based multi-objective task scheduling optimization model in cloud environments
- 1.1k Downloads
Optimizing task scheduling in a distributed heterogeneous computing environment, which is a nonlinear multi-objective NP-hard problem, plays a critical role in decreasing service response time and cost, and boosting Quality of Service (QoS). This paper, considers four conflicting objectives, namely minimizing task transfer time, task execution cost, power consumption, and task queue length, to develop a comprehensive multi-objective optimization model for task scheduling. This model reduces costs from both the customer and provider perspectives by considering execution and power cost. We evaluate our model by applying two multi-objective evolutionary algorithms, namely Multi-Objective Particle Swarm Optimization (MOPSO) and Multi-Objective Genetic Algorithm (MOGA). To implement the proposed model, we extend the Cloudsim toolkit by using MOPSO and MOGA as its task scheduling algorithms which determine the optimal task arrangement among VMs. The simulation results show that the proposed multi-objective model finds optimal trade-off solutions amongst the four conflicting objectives, which significantly reduces the job response time and makespan. This model not only increases QoS but also decreases the cost to providers. From our experimentation results, we find that MOPSO is a faster and more accurate evolutionary algorithm than MOGA for solving such problems.
KeywordsCloud computing Task scheduling Multi-objective particle swarm optimization Multi-objective genetic algorithm Jswarm Cloudsim
The work presented in this paper was supported by the Australian Research Council (ARC) under Discovery Project DP140101366. The Authors also would like to thank Mr Chaosong Nie for his kind help in implementing the MOGA algorithm.
- 2.Buyya, R., Beloglazov, A., Abawajy, J.: Energy-efficient management of data center resources for cloud computing: A vision, architectural elements, and open challenges. arXiv preprint arXiv:1006.0308 (2010)Google Scholar
- 3.Calheiros, R.N., Ranjan, R., De Rose, C.A.F., Buyya, R.: Cloudsim: A novel framework for modeling and simulation of cloud computing infrastructures and services. Arxiv preprint arXiv:0903.2525 (2009)Google Scholar
- 7.Guo, L., Zhao, S., Shen, S., Jiang, C.: Task scheduling optimization in cloud computing based on heuristic algorithm. J. Netw. 7(3), 547–553 (2012)Google Scholar
- 8.Hadka, D.: MOEA Framework A Free and Open Source Java Framework for Multiobjective Optimization, [Online], Available: http://www.moeaframework.org/
- 9.Juhnke, E., Dörnemann, T., Böck, D., Freisleben, B.: Multi-objective scheduling of BPEL workflows in geographically distributed clouds. In: 4th IEEE International Conference on Cloud Computing, pp. 412–419 (2011)Google Scholar
- 10.Lei, Z., Yuehui, C., Runyuan, S., Shan, J., Bo, Y.: A task scheduling algorithm based on PSO for grid computing. Int. J. Comput. Intell. Res. 4(1), 37–43 (2008)Google Scholar
- 17.Priya, B., Pilli, E.S., Joshi, R.C.: A survey on energy and power consumption models for Greener Cloud. In: Advance Computing Conference (IACC), 2013 I.E. 3rd International, 2013, IEEE, pp. 76–82Google Scholar
- 19.Ramezani, F., Lu, J., Hussain, F.: Task scheduling optimization in cloud computing applying multi-objective particle swarm optimization. International Conference on Service Oriented Computing (ICSOC), pp. 237–251 (2013)Google Scholar
- 23.Song, B., Hassan, M.M., Huh, E.: A novel heuristic-based task selection and allocation framework in dynamic collaborative cloud service platform. In: 2nd IEEE International Conference on Cloud Computing Technology and Science (CloudCom), pp. 360–367 (2010)Google Scholar
- 30.Top 500 Supercomputing Sited, [Online], Available: http://www.top500.org/system/176223
- 34.Zhang, Y., Lu, C., Zhang, H., Han, J.: Active vibration isolation system integrated optimization based on multi-objective genetic algorithm. In: IEEE 2nd International Conference on Computing, Control and Industrial Engineering (CCIE), pp. 258–261 (2011)Google Scholar