一种任务优先级的综合设计方法

提出了一种基于优先级表设计的调度算法.将任务的相对截止期和空闲时间这两个特征参数结合起来,综合设计任务的优先级表,使得截止期越早或空闲时间越短,任务的优先级越高,而且任务的优先级由相对截止期和空闲时间惟一确定.对于任意一个任务,可通过对设计的优先级表进行二元多点插值获得相应任务的惟一优先级.与传统的EDF和LSF算法进行仿真比较,仿真结果表明,通过优先级表设计方法来确定任务的优先级,提高了任务调度的成功率,降低了任务截止期的错失率.该方法可应用于实时系统中实时任务的动态调度中.

An Integrated Design Method of Task Priority

A scheduling algorithm based on priority table design is presented in this paper. Any two characteristic parameters (e.g., relative deadline and slack) of a task are combined to design its priority table so that the deadline is nearer or the slack is shorter, the priority is higher. The priority of a task is uniquely determined by its relative deadline and slack. For any task, its unique priority can be obtained by using Lagrange interposing algorithm on the designed priority table. Compared with the classical EDF and LSF policies, simulated results show that the proposed algorithm improves the efficiency of task scheduling, i.e., to designate the priority of a task, increases the succeed ratio of task scheduling, and decreases the missed deadline percentage. The proposed algorithm can be applied to dynamically schedule real-time tasks in real-time systems.