Research On Genetic Particle Swarm Optimization Algorithm Based On Cloud Computing

Cloud computing,as a hot technology in IT field,has attracted wide attention of scholars in various fields because of its powerful processing ability.The key technology in cloud computing is the design and application of cloud computing task scheduling algorithms.Task scheduling is a typical NP-complete problem,intelligent algorithms with advantages such as simplicity,generality,robustness,and suitable for parallel processing have become the research hotspots in the field of cloud computing task scheduling.Particle swarm optimization(PSO)and genetic algorithm(GA)are important intelligent algorithms to solve this problem.Based on the analysis of the advantages and disadvantages of PSO and GA,this paper proposes a cloud computing task based on genetic particle swarm algorithm,which satisfy the reasonable allocation and utilization of resources in cloud environment and efficiently scheduling of massive tasks submitted by users.Specific research work is as follows:(1)Aiming at the shortcomings of PSO in the task scheduling,it is easy to fall into the local optimal solution and the poor optimization ability,this paper proposes an enhanced particle swarm optimization algorithm(EPSO)that on the basis of adaptive inertia weight,the correlation between random factors should be properly integrated.The experimental results show that improved algorithm can not only improve the ability of particle swarm optimization,but also avoid falling into local optimum,so as to get a scheduling scheme with better time and cost.(2)The EPSO is introduced into the mutation operation of the genetic algorithm.The mutation operator is reconstructed by the current optimal solution and the global optimal solution of the PSO,the enhanced genetic particle swarm hybrid algorithm(GA EPSO)has a faster convergence speed without falling into the local optimal solution.The experimental results show that the GA_EPSO not only has a fast convergence speed,but also has a significant improvement in task scheduling efficiency.