基于李雅普诺夫优化的容器云队列在线任务和资源调度设计

为在保证任务服务质量(QoS)的条件下提高容器云资源利用率,提出一种基于李雅普诺夫的容器云队列任务和资源调度优化策略。首先,在云计算服务排队模型的基础上,通过李雅普诺夫函数分析任务队列长度的变化;然后,在任务QoS的约束下,构建资源功耗的最小化目标函数;最后,利用李雅普诺夫优化方法求解最小资源功耗目标函数,获得在线的任务和容器资源的优化调度策略,实现对任务和资源调度进行整体优化,从而保证任务的QoS并提高资源利用率。CloudSim仿真结果表明,所提的任务和资源调度策略在保证任务QoS的条件下能获得高的资源利用率,实现容器云在线任务和资源优化调度,并且为基于排队模型的云计算任务和资源整体优化提供必要的参考。

Online task and resource scheduling designing for container cloud queue based on Lyapunov optimization method

To improve the resource utilization with Quality of Service (QoS) guarantee, a task and resource scheduling method under Lyapunov optimization for container cloud queue was proposed. Firstly, based on the queueing model of cloud computing, the Lyapunov function was used to analyze the variety of the task queue length. Secondly, the minimum energy consumption objective function was constructed under the task QoS guarantee. Finally, Lyapunov optimization method was used to solve the minimum cost objective function to obtain an optimization scheduling policy for the online tasks and container resources, improving the resource utilization and guaranteeing the QoS. The CloudSim simulation results show that, the proposed task and resource scheduling policy achieves high resource utilization under the QoS guarantee, which realizes the online task and resource optimization scheduling of container cloud and provides necessary reference for cloud computing task and resource overall optimization based on queuing model.