Affiliations: College of Computer and Information Engineering, Inner Mongolia Agricultural University, Hohhot, China
Correspondence:
[*]
Corresponding author. Xueliang Fu, College of Computer and Information Engineering, Inner Mongolia Agricultural University, Hohhot, China. E-mail: fuxl@imau.edu.cn.
Abstract: Task scheduling in the cloud environment is a hot issue in current research. Aiming at the task scheduling problem in cloud environment, this paper analyses the scheduling model of cloud tasks, proposed an improved genetic algorithm (PGA) based on phagocytosis, changed the crossover operation of standard genetic algorithm (GA), formed a sub-chromosome individual after phagocytosis of two mother chromosomes, another individual was generated randomly, and the new individual generated after phagocytosis is determined by the fitness function and the load-balancing standard deviation, so that the evolution process can ensure a high proportion of high-quality individuals in the population. Ensure the diversity of the population. Then a multi-population hybrid coevolutionary genetic algorithm (MPHC_GA) is adopted, which uses the Min-Min algorithm to generate initial multiple sub-populations, and these sub-populations are evolved by standard genetic algorithm (GA) and improved genetic algorithm (PGA) based on phagocytosis. The simulation results show that the proposed algorithm is effective in cloud task scheduling.
