I. Introduction
Undeniably, the majority of practical real-time systems must be able to sustain several reliability threats, especially if the system is safety-critical and hard real-time characteristics must be satisfied, as prevalent in the automotive and aerospace sector. More precisely, the proper system functioning must be maintained at any point in time, comprising not only functional but also temporal correctness, i.e., a delivered result must be correct and, moreover, be obtained previous to a specified deadline. In order to ensure these properties, manifold hardware as well as software techniques have been developed so far by means of which such systems' reliability can be increased when so-called soft errors or transient faults occur, e.g., spatial isolation of certain components, hardware redundancy, remapping of logical system functionalities onto a subset of hardware resources, monitoring, and re-execution of erroneous software jobs [16]. However, these strategies are not necessarily sufficient or even applicable in all cases, since i) not every technique is fruitful with respect to each type of faults, and ii) online adaption performed in the course of fault-recovery may lead to uncertain execution behavior.