SAMPGA task scheduling algorithm in cloud computing

• Published in: 2017 36th Chinese Control Conference (CCC) pp. 5633 - 5637
• Main Authors: Xing Jia Wei, Wang Bei, Li Jun
• Format: Conference Proceeding
• Language: English
• Published: Technical Committee on Control Theory, CAA 01.07.2017
• Subjects: Algorithm design and analysis; Cloud computing; Convergence; Genetic algorithms; multi-population genetic algorithm; Processor scheduling; simulated annealing algorithm; Sociology; Statistics; task scheduling
• ISSN: 2161-2927
• DOI: 10.23919/ChiCC.2017.8028252

As cloud computing is growing rapidly, efficient task scheduling algorithm plays a vital role to improve the resource utilization and enhance overall performance of the cloud computing environment. However, task scheduling is the severe challenge needed to solve urgently in cloud computing. Therefore, the simulated annealing multi-population genetic algorithm (SAMPGA) is proposed for task scheduling in cloud computing, which is the combination of simulated annealing algorithm (SA) and multi-population genetic algorithm (MPGA) in this paper. In population initialization, SAMPGA adopts max-min algorithm to enhance the search efficiency. SA incorporated into SAMPGA is employed to avoid local optimum and improve the performance of global optimum, while a family evolution strategy based on adaptive mechanism in MPGA is proposed to fmd better solution and improve convergence speed. Finally, experiments are conducted to evaluate the efficiency of the proposed method in MATLAB. Compared with MPGA, SA and simulated annealing genetic algorithm (SAGA), the results of simulation show that the SAMPGA has more excellent performance in terms of the completion time, completion cost, convergence speed and degree of load imbalance.