Bounding Time in Mixed-Criticality Systems

Determining the appropriate WCETs for LO modes is nontrivial in MC systems. Considering a very low WCET for tasks can improve the processor utilization by scheduling more tasks in that mode; on the other hand, using a larger WCET ensures that the mode switches are minimized, thereby improving the QoS for all tasks, albeit at the cost of processor utilization. Hitherto, no analytical solutions are proposed to determine WCETs in lower criticality modes. In this regard, in this chapter, we propose a theoretical scheme to determine WCETs, to make a trade-off between the number of scheduled tasks at design-time and the number of dropped LC tasks at run-time as a result of frequent mode switches. However, these approaches consider a statically low WCET for each task which cannot adapt to dynamism at run-time. Therefore, we then consider the run-time behavior of tasks and propose a learning-based approach that dynamically monitors the tasks’ execution times and adapts the low WCETs to improve the QoS.