针对实时系统中的偶发任务和非周期任务,基于资源预留方法提出了一种利用状态反馈调整资源分配的调度策略.该策略的主要目标是当偶发作业负载在一定范围内变化时,保证偶发任务满足其时限,并使非周期任务的平均响应时间尽可能地小.文章首先通过状态方程描述偶发任务完成时间与预留资源的关系,然后利用状态反馈极点配置为偶发任务分配资源,最后将该闭环反馈调度系统看成是一种分段仿射系统,建立分段仿射二次型Lyapunov函数讨论算法的稳定性.最后通过实验说明,与传统调度算法相比,所提出的调度策略在调度负载不可预测的偶发任务时具有更好的性能.%Aim. The introduction of the full paper reviews some papers in the open literature, points out what we believe to be their shortcomings, and then proposes what we believe to be a novel and better scheduler. Sections 1 through 3 explain the design of our better scheduler. Section 1 briefs resource reservation scheduler. Section 2 briefs what is already known about resource allocation for different tasks. The core of section 3 consists of; (1) the goal of our scheduler is to make the sporadic jobs satisfy their deadlines when their loads vary in a certain range and to make the average response time of non-periodic jobs as short as possible; (2 ) after providing a precise mathematical model of the scheduler, a controller to adjust the resource allocation for different tasks is designed; (3) the global stability of our scheduler is discussed as a piecewise affine system. Experimental results, presented in Figs. 2 through 6, and their analysis demonstrate preliminarily the effectiveness and advantage of our scheduling algorithm when the sporadic tasks vary unpredictably.
展开▼
