基于云引力搜索的负载调度算法  

Load Scheduling Algorithm Based on Cloud Gravity Search

作　　者：刘丰年 LIU Feng-nian(College of Applied Engineering,Henan University of Science and Technology,Sanmenxia 472000,China;Sanmenxia Polytechnic,Sanmenxia 472000,China)

机构地区：[1]河南科技大学应用工程学院,河南三门峡472000 [2]三门峡职业技术学院,河南三门峡472000

出　　处：《数学的实践与认识》2020年第19期296-304,共9页Mathematics in Practice and Theory

基　　金：河南省重点科技攻关基金项目(14210221042);河南省教育厅科学技术研究重点基础研究计划基金项目(14A520048)。

摘　　要：针对云计算环境中的数据和负载调度问题,提出一种基于云引力搜索的负载调度算法.首先,随机初始化搜索空间中粒子的位置和速度;其次,根据适应度函数计算得出每个粒子的适应度值,并推导出下一个粒子的速度和位置;最后,将粒子的最优解分配给cloudlets完成负载调度.该算法通过使用基于适应值的粒子提升了虚拟机的利用率,从而降低了cloudlets分配至虚拟机所需的传输时间和总成本.采用了cloudsim软件对本文算法与现有的流行算法进行了仿真和比较,实验结果表明在将cloudlets分配至虚拟机的过程中,算法具有较少的传输时间和较低的负载调度成本.Aiming at the problem of data and load scheduling in cloud computing environment,a load scheduling algorithm based on cloud gravity search is proposed.Firstly,the position and speed of the particles in the search space are initialized randomly;secondly,the fitness value of each particle is calculated according to the fitness function,and the speed and position of the next particle is deduced;finally,the optimal solution of the particles is assigned to cloudlets to complete the load scheduling.The algorithm improves the utilization of virtual machine by using fitness based particles,thus reducing the transmission time and total cost of cloudlets allocated to virtual machine.By using cloudsim software,the algorithm is simulated and compared with the existing popular algorithm.The experimental results show that the algorithm has less transmission time and lower load scheduling cost in the process of distributing cloudlets to virtual machine.

关 键 词：负载调度 云引力搜索 云计算 粒子 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程] TP393.0[自动化与计算机技术—控制科学与工程]