实时嵌入式异构环境下多优先级混合任务调度动态策略

Dynamic scheduling strategy for multi priority hybrid tasks in heterogeneous environment of real-time embedded systems

针对现有异构环境下的调度策略,引入迫切密度和剩余价值密度,分析迫切密度和剩余价值密度调节任务执行紧急程度的影响、对优先级制定,通过构建单有向无环图(DAG)系统模型实现了混合任务的动态调度。仿真实验结果表明:该调度策略在系统负载较高的情况下,仍有较优的任务执行效能和避免颠簸现象。

Introduce concept of urgency density and surplus value density,analyze influence of urgency density and surplus value density on priority setting,adjusted the task execution degree of emergency based on weight coefficient and acceleration factor,and dynamic scheduling of hybrid task is achieved based on constructing single directed acyclic graph（ DAG） system model. Simulation results show that the proposed scheduling strategy can achieve better task execution efficiency and avoid thrashing even at higher load level.