Application of Self-adaptive Chaos Particle Swarm Optimization in Task Scheduling for Cloud Computing
Author(s): ZHANG Xiao-li
Pages: 161-165
Year: 2016 Issue: 8
Journal: Computer Technology and Development
Keyword: cloud computing; task scheduling; Particle Swarm Optimization ( PSO); chaos;
Abstract: Tasks scheduling is an important issue to be resolved in cloud computing research. In order to overcome the defects of tradition-al PSO easy to fall into local optimum,in view of procedure model framework of cloud computing,the chaos optimization search tech-nique is applied to the particle swarm optimization,and an adaptive chaotic particle swarm algorithm of task scheduling based on Tent mapping is presented. It combines the fast convergence of PSO and the ergodic property of chaotic motion,with chaotic assignment way in initializing particle position,and then adaptively adjusts its inertia weight according to the fitness value of each individual particle,up-dating chaos location for particle swarm individual to help themselves escape from local optima. Through simulation experiment on the CloudSim platform,the results show that the ACPOS,with a good real-time performance and optimization ability,significantly reduces the completion time of the task,which is an efficient task scheduling algorithm.
Pages: 161-165
Year: 2016 Issue: 8
Journal: Computer Technology and Development
Keyword: cloud computing; task scheduling; Particle Swarm Optimization ( PSO); chaos;
Abstract: Tasks scheduling is an important issue to be resolved in cloud computing research. In order to overcome the defects of tradition-al PSO easy to fall into local optimum,in view of procedure model framework of cloud computing,the chaos optimization search tech-nique is applied to the particle swarm optimization,and an adaptive chaotic particle swarm algorithm of task scheduling based on Tent mapping is presented. It combines the fast convergence of PSO and the ergodic property of chaotic motion,with chaotic assignment way in initializing particle position,and then adaptively adjusts its inertia weight according to the fitness value of each individual particle,up-dating chaos location for particle swarm individual to help themselves escape from local optima. Through simulation experiment on the CloudSim platform,the results show that the ACPOS,with a good real-time performance and optimization ability,significantly reduces the completion time of the task,which is an efficient task scheduling algorithm.
Related Articles