云计算环境下基于粒子群算法的多目标优化  

Multi-objective optimization based on particle swarm optimization algorithm in cloud computing

作　　者：郭力争[1,2] 耿永军[1] 姜长源[2] 王军豪[2] 张娜[2] 赵曙光[2] 

机构地区：[1]河南城建学院计算机科学与工程系,河南平顶山467036 [2]东华大学信息学院,上海201620

出　　处：《计算机工程与设计》2013年第7期2358-2362,共5页Computer Engineering and Design

基　　金：国家自然科学基金项目(70971020);河南省科技计划重点科技攻关基金项目(122102210412);河南省教育厅科学技术研究重点基金项目(12A520006)

摘　　要：为了优化资源的部署调度,需要考虑处理费用、传输费用,并提高云计算的性能。对云计算环境下特点进行了研究,把云计算环境下的数据部署和任务调度问题映射为处理交互图,对处理交互图进行分析、提出了多目标优化模型,并通过粒子群算法对多目标模型进行优化。仿真结果表明,该多目标优化模型和算法不但能优化处理时间、传输时间,也能优化处理费用和传输费用。In cloud computing, resource scheduling is a hot issue in rescent research, in order to optimize the resource scheduling, need to consider the processing, the transfering cost and to improve the performance. The characteristics of cloud computing is studied, then, the data placement and task scheduling are mapped to processors interaction graph. A multi-objective optimizing model is formulated through analyzing the processors interaction graph. Based on the proposed model, a particle swarm optimzation algorith is used to optimize the data deployment and task scheduling. The simulation results show that the multi-objective model is not only optimize the time of processing and transfering, but alos optimize the the cost of processing and transfering.

关 键 词：云计算 粒子群算法 数据部署 任务调度 多目标优化 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]