XJIPC OpenIR  > 多语种信息技术研究室
基于改进粒子群算法的云计算任务调度策略
马亮
Subtype硕士
Thesis Advisor李晓
2013-05-24
Degree Grantor中国科学院大学
Place of Conferral北京
Degree Discipline计算机应用
Keyword云计算 任务调度 粒子群算法 负载均衡
Other Abstract

如何进行合理高效的任务调度是云计算研究的重要问题。本文结合新疆电子政务云系统,针对如何提高云计算任务调度的效率和负载均衡的问题,做前期的研究和探索。本文在对云计算环境及其任务的详细量化分析的基础上,结合实际问题对粒子群调度算法进行变异和修改,提出了一种基于改进粒子群算法的云计算任务调度算法,着重从任务完成时间和负载均衡两方面对云计算中的任务调度进行优化。改进的优化方案利用混沌映射对粒子群的初始化进行了均匀化处理,降低了求解次数和难度;系统出现负载失衡或算法陷入早熟收敛时,引入混沌变异策略,从而在全局收敛的同时保证一定的负载均衡性。将该改进的粒子群优化算法运用于云计算任务调度策略,解决了寻找任务-资源映射匹配对这一目标优化问题。通过实验表明,该算法具有较好的性能,不仅使得任务完成时间高效,并且有效的兼顾了负载均衡,使系统资源尽可能的得到了充分利用。

;

How reasonably efficient task scheduling is an important issue for cloud computing research.In this paper, based on detailed quantitative analysis of the environment and its task of cloud computing, this article proposed improved particle swarm scheduling algorithm, focus on task completion time and load balancing to optimize task scheduling in cloud computing. Improved optimization program using chaotic map initialization of the particle swarm homogenization, reducing the number and difficulty of solving; when the system load imbalance or premature convergence algorithm, the introduction of the chaotic mutation strategy, result in global convergence and guarantee a certain load balancing. The improved particle swarm optimization algorithm used in cloud computing, task scheduling strategy, resolve to find the task-resource mapping match this objective optimization problem. Experiments show that the algorithm has better performance, not only makes the task completion time efficient and effective balance between load balancing, system resources are fully utilized.

Document Type学位论文
Identifierhttp://ir.xjipc.cas.cn/handle/365002/2486
Collection多语种信息技术研究室
Affiliation中国科学院新疆理化技术研究所
Recommended Citation
GB/T 7714
马亮. 基于改进粒子群算法的云计算任务调度策略[D]. 北京. 中国科学院大学,2013.
Files in This Item:
File Name/Size DocType Version Access License
基于改进粒子群算法的云计算任务调度策略.(1018KB)学位论文 开放获取CC BY-NC-SAView Application Full Text
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[马亮]'s Articles
Baidu academic
Similar articles in Baidu academic
[马亮]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[马亮]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: 基于改进粒子群算法的云计算任务调度策略.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.