Real-time systems that can change their functionality over time and execute in different operational “modes” can be found in several application domains from safety-critical avionic and automotive control systems to multimedia smart devices. Such systems may have to adapt their behavior during runtime to changing conditions in the environment. For example, in the automotive domain advanced driver-assistance solutions are implemented in order to improve the active safety. At runtime, these shall smartly prepare and react to a possible critical situation.
However, when switching between different operational modes, functionalities of the different modes may coexist. This overlap can further lead to transient overload situations that can propagate as “waves” between the system’s components thus challenging the real-time behavior of the entire system.
When a multi-mode system is part of a hard real-time embedded system it is imperative to guarantee that timing constraints are not violated at any moment of the system’s execution (i.e. neither in the individual modes, nor during the transition phases).
Predicting timing behavior is essential for the design of real-time systems that can switch between different operational modes at runtime. However, known approaches that address the problem of timing analysis for multi-mode real-time systems focus only on single-processor architectures. When considering multi-mode distributed systems, the analysis of the timing behavior becomes more complicated. The local effect (e.g. on individual single-core or multi-core ECUs) of a mode change will impact the other components in the system.
The goal of this project is the development of a formal methodology for the analysis and optimization of distributed multi-mode multi-core systems. The main aspects in this project are:
Mircea Negrean
Sebastian Klawitter (HiWi/ Java Programmierung)
Torben Schmidt (Studienseminar)
Deutsche Forschungsgemeinschaft (German Research Foundation, DFG)
