云计算环境下基于改进遗传算法的多维约束任务调度研究

发布时间：2018-08-23 14:38

【摘要】：云计算环境下计算任务数量十分庞大和复杂,为云计算效率的提升带来了一定的挑战,有效的计算任务调度策略是保障云计算效率的有力手段.如何合理的对云计算资源进行分配以及设计高效的计算任务调度策略,使得所有任务执行完成满足多维约束条件是当前研究热点之一.本文在遗传算法基础上,提出了一种考虑时间、成本、CPU、内存和带宽等多维约束的任务调度算法MCGA,在算法的编码与解码、适应度函数、交叉变异等操作环节上进行了改进,并详细给出算法的执行步骤,最后在CloudSim平台上进行了仿真实验.实验结果表明,本文提出的算法能够有效的达到优化任务调度效率,同时又可提升云计算资源利用率的目的,为云计算环境下任务调度提供了一种可行的思路和方法.
[Abstract]:The number of computing tasks in cloud computing environment is very large and complex, which brings some challenges to the efficiency of cloud computing. Effective task scheduling strategy is a powerful means to ensure the efficiency of cloud computing. How to reasonably allocate cloud computing resources and design efficient computing task scheduling strategy to make all tasks complete to meet the multi-dimensional constraints is one of the current research hotspots. On the basis of genetic algorithm, this paper presents a task scheduling algorithm MCGA, which takes into account multi-dimensional constraints such as time, cost, memory and bandwidth, and improves the algorithm in coding and decoding, fitness function, crossover mutation and so on. The implementation steps of the algorithm are given in detail. Finally, the simulation experiments are carried out on the CloudSim platform. Experimental results show that the proposed algorithm can effectively achieve optimal task scheduling efficiency, and at the same time can improve the utilization of cloud computing resources. It provides a feasible idea and method for task scheduling in cloud computing environment.
【作者单位】：上海计算机软件技术开发中心;上海市计算机软件评测重点实验室;上海海事大学信息工程学院;华东理工大学信息科学与工程学院;
【基金】：上海市科技人才计划项目(16XD1421500)资助上海市软科学研究计划项目(1569210660E)资助
【分类号】：TP18;TP3

【相似文献】