信息网络安全 ›› 2017, Vol. 17 ›› Issue (1): 23-28.doi: 10.3969/j.issn.1671-1122.2017.01.004

• • 上一篇    下一篇

融合负载均衡和蝙蝠算法的云计算任务调度

王东亮1,2(), 衣俊艳3, 李时慧1, 王洪新4   

  1. 1.国家行政学电子政务研究中心, 北京 100089
    2.北京建筑大学资产与后勤管理处,北京100044
    3. 北京建筑大学电气与信息工程学院,北京100044
    4.中国图书进出口(集团)总公司数字发展中心, 北京 100020
  • 收稿日期:2016-11-01 出版日期:2017-01-20 发布日期:2020-05-12
  • 作者简介:

    作者简介: 王东亮(1980—),男,山东,博士,讲师,主要研究方向为公共管理、大数据挖掘与处理;衣俊艳(1978—)女,山东,副教授,博士,主要研究方向为人工智能与数据挖掘;李时慧(1982—),女,山东,讲师,博士,主要研究方向为教育经济与管理、信息教育;王洪新(1978—),女,山东,工程师,硕士,主要研究方向为云计算与大数据处理。

  • 基金资助:
    国家自然科学基金[61402032];安徽省高等学校自然科学研究一般项目[KJ2015B1105918]

Task Scheduling of Cloud Computing Based on Fusion of Load Balancing and Bat Algorithm

Dongliang WANG1,2(), Junyan YI3, Shihui LI1, Hongxin WANG4   

  1. 1. Electronic Government Research Center of Chinese Academy of Governance, Beijing 100089, China
    2. Asset and Logistics Management of Beijing University of Civil Engineering and Architecture, Beijing 100044, China
    3.College of Electrical and Information Engineering Beijing University of Civil Engineering and Architecture,Beijing 100044, China
    4. Digital Development Center of China National Publications Import and Export (Group)Corporation, Beijing 100020, China
  • Received:2016-11-01 Online:2017-01-20 Published:2020-05-12

摘要:

针对云计算虚拟机调度中存在的资源分配不均衡、蝙蝠算法收敛速度慢、寻优精度不高等缺点,文章提出了一种融合负载均衡和蝙蝠算法的云计算任务调度算法。利用负载均衡对蝙蝠种群数据进行初始化,提高初始样本数据解的质量;利用Powell局部搜索算法对当前最优解进行局部搜索,提高收敛速度和精度;利用改进蝙蝠算法对虚拟机进行分配时,充分利用物理机上的资源,达到了最优化目标。仿真实验表明,与其他标准蝙蝠算法和粒子优化算法相比,本文改进的算法有较快的收敛速度和较高的寻优精度。

关键词: 云计算任务调度, 蝙蝠算法, 负载均衡, 虚拟机调度, Powell局部搜索

Abstract:

For cloud computing resource allocation imbalance exists in the virtual machine scheduling, bat algorithm slow convergence speed and optimization accuracy is not high shortcomings, a method is proposed task scheduling of cloud computing based on fusion of load balancing and bat algorithm. Algorithm using load balancing to bat population data, improve the quality of the initial solution of the sample data; By Powell local search algorithm for the optimal solution for the current local search and improve the convergence speed and accuracy; when using the improved bat algorithm to allocate the virtual machine, algorithm make full use of the resources on the physical machine to achieve the optimization goal. Simulation results show that the improved algorithm has faster convergence speed and higher searching accuracy compared with other standard bat algorithm and particle swarm optimization algorithm.

Key words: task scheduling of cloud computing, bat algorithm, load balancing, virtual machine scheduling, Powell local search

中图分类号: