吉林大学学报(理学版)

• 计算机科学 • 上一篇    下一篇

基于改进粒子群算法的云计算服务部署优化

王晓天1, 韩啸2   

  1. 1. 大连东软信息学院 计算机科学与技术系, 辽宁 大连 116000; 2. 吉林大学 学报编辑部, 长春 130012
  • 收稿日期:2016-07-01 出版日期:2017-03-26 发布日期:2017-03-24
  • 通讯作者: 韩啸 E-mail:hanxiao@jlu.edu.cn

Cloud Computing Service Deployment OptimizationBased on Improved Particle Swarm Algorithm

WANG Xiaotian1, HAN Xiao2   

  1. 1. Department of Computer Science and Technology, Dalian Neusoft University of Information, Dalian 116000, Liaoning Province, China; 2. Editorial Department of Journal of Jilin University, Changchun 130012, China
  • Received:2016-07-01 Online:2017-03-26 Published:2017-03-24
  • Contact: HAN Xiao E-mail:hanxiao@jlu.edu.cn

摘要: 针对云计算资源有限, 传统穷举搜索算法求解效率低的问题, 提出一种基于改进粒子群算法的云计算服务部署优化方法. 首先对云计算服务部署问题进行分析, 将其转换成一个多目标组合优化问题, 并建立相应的数学模型; 然后采用全局搜索能力强的粒子群算法对数学模型进行求解, 并针对标准粒子群算法收敛速度慢、 存在早熟现象进行改进; 最后通过仿真实验验证其可行性. 实验结果表明, 该方法可以快速找到最优的云计算服务部署方案.

关键词: 服务部署, 云计算系统, 优化算法, 粒子群算法

Abstract: Aiming at the problem that cloud computing resources we re limited, and the solving efficiency of exhaustive search algorithm was low, w e proposed a cloud computing service deployment optimization method ba sed on improved particle swarm algorithm. Firstly, the problem of clou d computing service deployment was analyzed, and it was transformed into a mult iobjective combinatorial optimization problem, and the corresponding mathemati cal model was established. Secondly, the particle swarm algorithm with global se arching ability was used to solve mathemati cal model, and the slow convergence rate of standard particle swarm algorithm an d premature convergence were improved. Finally, the feasibility was verified by simulation test. Experimental results show that the proposed method can quic kly find the best scheme for cloud computing service deployment.

Key words: optimization algorithm, service deployment, particle swarm algorithm, cloud computing system

中图分类号: 

  • TP393