一种多集群容器云资源调度优化方法  

A Multi-cluster Container Cloud Resource Scheduling Optimization Method

作　　者：徐胜超 熊茂华 XU Shengchao;XIONG Maohua(School of Date Science,Guangzhou Huashang College,Guangzhou 511300)

机构地区：[1]广州华商学院数据科学学院,广州511300

出　　处：《计算机与数字工程》2022年第11期2490-2496,共7页Computer & Digital Engineering

基　　金：国家自然科学基金项目(青年基金)(编号:61403219);广州华商学院校内导师制科研项目(编号:2022HSDS07)资助。

摘　　要：现有云资源调度方法由于应用技术自身的局限,存在资源调度时延过长、平均资源利用率过低的问题,无法满足用户需求,为此提出多集群容器云资源调度优化方法。深入探究云资源调度优化需求,以此为基础搭建多集群容器云框架,弥补现有边缘容器云框架的不足。制定虚拟机-容器调度机制,降低任务在主机间的迁移成本,描述云资源调度优化问题,应用BPSO(Binary Particle Swarm Optimization)算法求解云资源调度优化问题,即可实现多集群容器云资源的调度优化。通过实验数据对比发现,与现有方法相比较,所提方法资源调度时延较短,平均资源利用率较高,适合大力推广与应用。Due to the limitations of application technology,the existing cloud resource scheduling methods have the problems of long resource scheduling delay and low average resource utilization,which can not meet the needs of users.Therefore,a multicluster container cloud resource scheduling optimization method is proposed.It deeply explores the requirements for cloud resource scheduling optimization(focusing on the scheduling needs of cloud users),and builds a multi cluster container cloud framework on this basis to make up for the shortcomings of the existing edge container cloud framework.It formulates the virtual machine container scheduling mechanism,reduce the migration cost of tasks between hosts,describes the cloud resource scheduling optimization problem,and applies BPSO algorithm to solve the cloud resource scheduling optimization problem,so as to realize the scheduling optimization of multi cluster container cloud resources.Through the comparison of experimental data,it is found that compared with the existing methods,the proposed method has shorter resource scheduling delay and higher average resource utilization,indicating that the proposed method has better optimization effect of cloud resource scheduling and is suitable for vigorous promotion and application.

关 键 词：多集群容器 云资源 调度优化 二进制粒子群算法 虚拟机-容器调度 

分 类 号：TP393.4[自动化与计算机技术—计算机应用技术]