基于Docker集群的弹性任务调度模型构建  

Research on Flexible Task Scheduling Method and Process Based on Docker Cluster

作　　者：孙强强[1] SUN Qiang-qiang(Harbin University of Technology,Harbin 150000 China)

机构地区：[1]哈尔滨工业大学,黑龙江哈尔滨150000

出　　处：《自动化技术与应用》2023年第8期6-9,共4页Techniques of Automation and Applications

摘　　要：针对Docker集群访问量具有随机性和不确定性的问题,在提出基于多指标灰色负载预测基础上,通过增加或减少应用容器的方式,实现集群任务的弹性调度,实现集群应用性能和负载均衡。实验结果表明,所提出的基于多指标灰色负载预测算法的弹性任务调度策略,可适应web应用的动态变化,保证高负载状态下应用可即时响应,低负载状态下集群的资源利用率最高。Aiming at the problem of random and uncertain access of docker cluster,based on multi index grey load prediction,the flexible scheduling of cluster tasks is realized by adding or reducing application containers,and the cluster application performance and load balance are realized.The results show that the flexible task scheduling strategy based on multi index gray load prediction al-gorithm proposed in this study can adapt to the dynamic changes of web applications,ensure that the application can respond im-mediately under high load state,and the cluster resource utilization is the highest under low load state.

关 键 词：Docker集群 任务调度 负载均衡 灰色预测 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]