首页 | 本学科首页   官方微博 | 高级检索  
检索        

云计算中基于进化算法的任务调度策略
引用本文:李欢,虞慧群.云计算中基于进化算法的任务调度策略[J].医学教育探索,2015(4):556-562.
作者姓名:李欢  虞慧群
作者单位:华东理工大学计算机科学与工程系, 上海 200237;上海市计算机软件评测重点实验室, 上海 201112,华东理工大学计算机科学与工程系, 上海 200237
基金项目:国家自然科学基金(61173048)
摘    要:任务调度是云计算的关键问题之一,它的调度策略与算法直接影响到云计算系统的性能与成本。通过研究基于粒子群算法和遗传算法的任务调度策略,提出了一种基于进化策略的PSO-CM算法。该算法通过在粒子群算法中引入遗传算法的交叉变异策略来提高粒子群算法的全局收敛效果,并且证明了PSO-CM算法是一种全局收敛算法。Matlab仿真实验表明,该算法能够达到全局收敛,且收敛速度和稳定性优于传统的调度算法。

关 键 词:云计算  任务调度  粒子群算法  遗传算法  全局收敛
收稿时间:2014/9/24 0:00:00

Task Scheduling Strategy Based on Evolutionary Algorithms in Cloud Computing
LI Huan and YU Hui-qun.Task Scheduling Strategy Based on Evolutionary Algorithms in Cloud Computing[J].Researches in Medical Education,2015(4):556-562.
Authors:LI Huan and YU Hui-qun
Institution:Department of Computer Science and Engineering, East China University of Science and Technology, Shanghai 200237, China;Shanghai Key Laboratory of Computer Software Evaluating and Testing, Shanghai 201112, China and Department of Computer Science and Engineering, East China University of Science and Technology, Shanghai 200237, China
Abstract:Task scheduling is one of the key issues on the cloud computing, whose scheduling strategy and algorithm plays a direct effect on the performance and the cost of the cloud computing systems. By analyzing the particle swarm algorithm and the genetic algorithm, this paper proposes an evolutionary-strategy based PSO-CM algorithm to manage cloud tasks schedule. The proposed algorithm can improve the global convergence of PSO by introducing the crossover and mutation strategy of the genetic algorithm. The experiments on Matlab show that the proposed algorithm can achieve global convergence and is superior to the traditional scheduling algorithms in convergence speed and stability.
Keywords:cloud computing  task schedule  particle swarm algorithm  genetic algorithm
点击此处可从《医学教育探索》浏览原始摘要信息
点击此处可从《医学教育探索》下载免费的PDF全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号