Abstract:

Unreasonable scheduling order will affect the execution time and real-time of the related task. Aiming at the complex relationship between IoT terminal tasks, this paper proposes a scheduling strategy using task relevance. This strategy designs a task model with the job polling group as the main body and establishes a priority factor matrix as the basis for task scheduling based on the deadline of task. For periodic task, the priority incremental matrix with the task relevance is generated to change the task priority dynamically for the real-time of predecessor task after each task is executed. For aperiodic task, this strategy constructs temporary job polling groups to preemptive scheduling. The experimental results show that this scheduling strategy can effectively reduce task execution time and shorten the response time of aperiodic task.

Key words: Internet of Things, task relevance, task scheduling, scheduling order, aperiodic task

摘要：

对于具有相关性的任务，调度顺序不合理将影响任务的执行时间和实时性。结合物联网终端任务间依赖关系复杂的特点提出了一种利用任务相关性的调度策略。该策略设计了以作业轮询组为主体的任务模型，根据任务时限建立了优先级因子矩阵作为任务调度的凭据，对于周期任务，在每个任务执行完毕后生成，以任务相关性为参数的增量矩阵用以动态修改任务优先级，使前驱任务能优先执行；对于非周期任务采用了构建临时作业轮询组的方式进行抢占调度。测试结果表明，该策略能够有效减少具有相关性的周期任务集执行时间和调度失败次数，缩短非周期任务响应时间。

关键词: 物联网, 任务相关性, 任务调度, 调度顺序, 非周期任务