基于改进的秃鹰搜索算法的虚拟机调度优化方法  

Virtual machine scheduling optimization method based on improved bald eagle search algorithm

作　　者：常岩 王勇 CHANG Yan;WANG Yong(School of Computer and Information Security,Guilin University of Electronic Technology,Guilin 541004,China;Guangxi Cloud Security and Cloud Service Engineering Technology Research Center Laboratory,Guilin University of Electronic Technology,Guilin 541004,China)

机构地区：[1]桂林电子科技大学计算机与信息安全学院,广西桂林541004 [2]桂林电子科技大学广西云安全与云服务工程技术研究中心实验室,广西桂林541004

出　　处：《计算机工程与设计》2024年第12期3631-3638,共8页Computer Engineering and Design

基　　金：国家自然科学基金项目(61662018、61661015、61831013);广西创新驱动发展专项基金项目(科技重大专项桂科AA18118031);桂林电子科技大学研究生教育创新计划基金项目(2023YCXS056)。

摘　　要：针对OpenStack云计算平台默认调度算法存在资源利用率低和负载不均衡的问题,提出一种基于改进的秃鹰搜索的调度算法(PieceWise bald and t-distribution eagle search,PBES),旨在最大化云数据中心的资源利用率和负载均衡。采用PieceWise混沌映射提高搜索算法的收敛速度和精度,引入t分布避免算法陷入局部最优解。综合考虑CPU、内存、磁盘和带宽等4种资源指标,采集真实环境下的数据并进行实验,其结果表明,相较OpenStack默认调度算法和粒子群算法,PBES算法在资源利用率和负载均衡方面都有显著提升。In response to the issues of low resource utilization and uneven load distribution in the default scheduling algorithm of the OpenStack cloud computing platform,an improved scheduling algorithm based on PieceWise bald and t-distribution eagle search(PBES)was proposed,aiming at maximizing resource utilization and load balancing in cloud data centers.The PieceWise chaotic mapping was utilized to enhance the convergence speed and precision of the search algorithm.The introduction of the t-distribution was utilized to prevent the algorithm from being trapped in local optima.The consideration of four resource indicators was encompassed,including CPU,memory,disk,and bandwidth.Through the collection of real-world data and conducting experiments,the results indicate that,compared to the default OpenStack scheduling algorithm and particle swarm optimization,significant improvements in resource utilization and load balancing are achieved using the PBES algorithm.

关 键 词：OPENSTACK 资源利用率 负载不均衡 优化调度 秃鹰搜索算法 混沌映射 T分布 

分 类 号：TP393.02[自动化与计算机技术—计算机应用技术]