Automotive Mixed Criticality DAG Function Scheduling Optimization Based on Edge Computing

As the high level autonomous vehicle has come to be regarded as the typical mixed-criticality cyber-physical system, the optimization approach of job scheduling has drawn more and more attention. When the conventional mixed-criticality theory is used to handle the scheduling problem, the low criticality functions are frequently degraded or abandoned at high system criticality levels, decreasing service satisfaction. This paper proposes an optimization method using edge computing to improve the performance of low criticality functions on the presumption that high criticality functions can meet the deadline requirements. The optimization method is based on the scenario of the future prospect of intelligent transportation and the new electronic/electrical information architecture of network connection. This research also provides some mixed-criticality function models to validate our methods. Weighted completion index is proposed to measure the scheduling effect of this situation, which also quantifies the level of improvement of edge computing-based scheduling over the conventional local scheduling method, in order to address the lack of evaluation of passengers' perception when vehicle soft real-time DAG functions are unable to meet the deadline.