基于纳什均衡的AUTOSAR任务到多核ECU的映射方法

随着汽车电子应用程序对处理器性能需求的不断提高,现代汽车电子系统中的电子控制单元(ECU)已升级为多核结构。多核ECU中的AUTOSAR应用程序的设计、实现和集成将面临新的挑战。其中一个重要的挑战是在映射任务到多核ECU的同时确保系统的实时性能。且在AUTOSAR静态配置过程中,实时系统的资源限制和调度分析使问题变得更加复杂。因此,文中提出了一种基于纳什均衡的AUTOSAR任务到多核ECU的映射方法。该方法将任务优先级应用于博弈过程中,对提高任务映射过程的效率具有非常重要的实用价值。最后,将所提方法应用于AUTOSAR标准的实例中。实验结果表明,所提方法在减少各个任务中可运行实体的最坏响应时间方面具有良好的表现。

Nash Equilibrium Based Method for Mapping AUTOSAR Tasks to Multicore ECU

With the growing requirements of automotive applications on processing power,the electronic control units (ECUs) in modern automotive system escalates to multicore architecture.The design,implementation and integration of AUTOSAR applications in multicore ECU will face new challenges.One of these challenges is mapping the tasks to multicore ECU while the real-time performance of system is ensured.In addition,the resource limitation and scheduling analysis in real-time system make the problems more complex in AUTOSAR static configuration.So this paper proposed a Nash equilibrium based method for mapping AUTOSAR tasks to multicore ECU.This method has important practical significance in improving the efficiency of task mapping process by applying the priority of tasks in game process.Finally,the proposed method was applied to the automotive electronic instance in AUTOSAR.The experimental results show that the proposed method has good performance in the worst case response time of the runnable entities in each task.