17 June 2020 in IEEE Transactions on Computers
The complexity of modern automotive systems grows with increasing user demands. A wide range of functionalities that these systems comprise is implemented as multiple control applications sharing platform resources. To ensure safe operation of the system, the applications must be executed periodically and deterministically in time. Although the applications are developed independently, the control performance of the resulting system depends on how the applications are integrated. A key integration challenge is hence to efficiently schedule the applications on shared resources with minimal control performance degradation. The three main contributions are: 1) a constraint programming model that solve the problem optimally, exploiting properties of the problem to reduce the computation time; 2) a fast heuristic called Flexi that only has a minor impact on the solution optimality; and 3) an experimental evaluation of the scalability and efficiency of the proposed approaches on a case study, in addition to several synthetic datasets. The results show that the heuristic provides a solution on average 5 times faster, finding a feasible solution in 31% more problem instances than the optimal approach within a time limit, while only sacrificing 0.5% of the control performance quality for the largest dataset.