改进K-means聚类的云任务调度算法  

Cloud Task Scheduling Algorithm Based on Modified K-means Clustering

作　　者：王欢[1] 李红辉[1] 张骏温[1] 

机构地区：[1]北京交通大学计算机与信息技术学院,北京100044

出　　处：《计算机与现代化》2017年第2期1-5,11,共6页Computer and Modernization

基　　金：国家863计划资助项目(2015AA043701)

摘　　要：针对云任务调度中存在的效率低、费用高等问题,提出一种基于改进K-means聚类算法的云任务调度算法。依据虚拟资源的硬件属性,使用改进聚类算法对虚拟资源进行聚类划分;计算任务偏好,使不同偏好的任务在不同的聚类中选择资源;考虑到调度费用问题,对每个聚类使用改进后的Min-min算法进行任务调度。针对K-means聚类算法初始聚类中心随机选取,易陷入局部最优解的问题,对聚类算法进行改进。最后,利用云仿真平台CloudSim进行实验,结果表明,与无聚类的调度算法相比,本文提出的算法在执行效率方面有所提高。Aiming at the problem of low efficiency and high cost in cloud task scheduling,a new cloud task scheduling algorithm based on modified K-means clustering is proposed. Based on the hardware properties of the virtual resources,the improved clustering algorithm is used to cluster the virtual resources. The task preferences are computed,so that different preferences of the task could select resources in different clusters. Taking into account the scheduling cost problem,the task scheduling is performed on each cluster by using the improved Min-min algorithm. We improve the K-means clustering algorithm aiming at the problem that the initial cluster centers are randomly selected and it is easy to fall into local optimal solution. Finally,the cloud simulation platform CloudSim is used to carry out the experiment,and the results show that the proposed algorithm can improve the efficiency compared with the non-clustering scheduling algorithms.

关 键 词：云计算 K-MEANS聚类 调度 CloudSim 

分 类 号：TP399[自动化与计算机技术—计算机应用技术]