Research on Cloud Computing Task Scheduling based on Improved Genetic Algorithm

Abstract

As an emerging technology, cloud computing is widely used by companies and enterprises because of its great commercial value. Effective scheduling of massive tasks submitted by users in the cloud environment has extremely important practical significance for increasing the core competitiveness of companies and enterprises and improving their economic benefits. According to the characteristics of cloud computing task scheduling, this paper studies the task scheduling from the aspects of how to minimize the maximum time span of the task, describes the task scheduling problem in cloud environment in detail,and proposes a scheduling strategy C2PGA. The GA algorithmuses a random function to initialize the population without guaranteeing the quality of the initial sample solution. Improve the quality of the initial sample solution by using the competitive crossover method to initialize the initial sample solution; Three-stage selection method is used to select the excellent individuals in the population, and the improved "phagocytosis mechanism" is used to replace the crossover operation of GA algorithm.Experiments show that the population generation method of C2PGA strategy is more uniform than the population generated by random function, and the number of excellent individuals in the initial individuals is more. And compared with other algorithms, C2PGA strategy has a better improvement in minimizing the maximum time span of the task.