摘要
粒子群优化(PSO)算法在云计算环境下任务调度方面应用十分广泛。针对算法易陷入局部最优、收敛速度慢的缺陷,从基本概念入手,在算法中加入改进的动态惯性权重和外部扰动策略,改善PSO算法的局部寻优能力,提高算法迭代后期收敛速度和搜索的精度,最后利用Cloudsim进行实验,将新算法与其他算法任务执行总的迭代次数的结果进行对比,新算法克服了粒子群算法的缺点,能够有效地平衡全局和局部搜索能力,任务的完成时间相对较少。
Particle swarm optimization（ PSO） algorithm is widely used in the task scheduling in Cloud computing environment. Aiming at the problem that the particle swarm algorithm is easy to fall into local optimum and has slow rate of convergence,this paper begins with basic concept,adds dynamic inertia weight and external disturbance strategy in particle swarm algorithm to improve the local-optimization. This algorithm can solve the problems of the slow convergence and low search precision. Finally,Cloudsim simulation platform is used for testing. Comparing the results of the number of iterations between the new algorithm and other algorithms at the execution time of task,new algorithm overcomes the shortcoming of particle swarm optimization,and can effectively balance the global search and local search. The completion time of the task is observably shorter.
作者
许向阳
张芳磊
Xu Xiangyang,Zhang Fanglei(School of Information Science and Engineering, Hebei University of Science and Technology, Shijiazhuang 050000, Chin)
出处
《信息技术与网络安全》
2018年第8期27-30,共4页
Information Technology and Network Security
