Design of Mixed-Criticality Applications on Distributed Real-Time Systems
We consider that the protection is achieved through a temporal- and space-partitioning scheme similar to Integrated Modular Avionics (IMA).
At the processing-level, we have proposed an optimization strategy to solve the following design problems: the mapping of tasks to PEs, the scheduling of tasks, the allocation of tasks to partitions, the task decomposition and the elevation of tasks, such that all applications are schedulable and the development costs are minimized. We have also extended the optimization strategy to take into account soft real-time applications and modified the cost function to capture the quality of service for these tasks.
At the network communication-level, we have proposed an optimization strategy to solve the following design problems: the scheduling of time-triggered frames, the fragmenting and packing of messages into frames, the routing of frames and the bandwidth of the rate-contraint (RC) frames, such that all messages are schedulable, and the worst-case end-to-end delay of the RC frames are minimized. We have also extended the strategy to take into best-effort traffic, and we have shown how using our strategy we can perform topology optimization to reduce the cost of the system
At the processing-level, we have proposed an optimization strategy to solve the following design problems: the mapping of tasks to PEs, the scheduling of tasks, the allocation of tasks to partitions, the task decomposition and the elevation of tasks, such that all applications are schedulable and the development costs are minimized. We have also extended the optimization strategy to take into account soft real-time applications and modified the cost function to capture the quality of service for these tasks.
At the network communication-level, we have proposed an optimization strategy to solve the following design problems: the scheduling of time-triggered frames, the fragmenting and packing of messages into frames, the routing of frames and the bandwidth of the rate-contraint (RC) frames, such that all messages are schedulable, and the worst-case end-to-end delay of the RC frames are minimized. We have also extended the strategy to take into best-effort traffic, and we have shown how using our strategy we can perform topology optimization to reduce the cost of the system
