Section: Bilateral Contracts and Grants with Industry

Bilateral Contracts with Industry

Ph.D. thesis under CIFRE collaboration with PSA

Participants: Aurélien Monot, Nicolas Navet, Françoise Simonot-Lion

The complexity of electronic embedded systems in cars is continuously growing. Hence, mastering the temporal behavior of such systems is paramount in order to ensure the safety and comfort of the passengers. As a consequence, the verification of end-to-end real-time constraints is a major challenge during the design phase of a car. The AUTOSAR software architecture drives us to address the verification of end-to-end real-time constraints as two independent scheduling problems respectively for electronic control units and communication buses.

First, we introduce an approach, which optimizes the utilization of controllers scheduling numerous software components that is compatible with the upcoming multicore architectures. We describe fast and efficient algorithms in order to balance the periodic load over time on multicore controllers by adapting and improving an existing approach used for the CAN networks. We provide theoretical result on the efficiency of the algorithms in some specific cases. Moreover, we describe how to use these algorithms in conjunction with other tasks scheduled on the controller [12] , [8] .

The remaining part of this research work addresses the problem of obtaining the response time distributions of the messages sent on a CAN network. First, we present a simulation approach based on the modelisation of clock drifts on the communicating nodes connected on the CAN network. We show that we obtain similar results with a single simulation using our approach in comparison with the legacy approach consisting in numerous short simulation runs without clock drifts. Then, we present an analytical approach in order to compute the response time distributions of the CAN frames. We introduce several approximation parameters to cope with the very high computational complexity of this approach while limiting the loss of accuracy. Finally, we compare experimentally the simulation and analytical approaches in order to discuss the relative advantages of each of the two approaches [20] , [8] .