A Distributed Task Scheduling Framework for Edge Computing and Cyber-Physical Systems

The continuously increasing amount of sensors in cyber-physical systems requires efficient edge computing architectures which follow the paradigm to process data where it emerges. Encapsulated software functions enable the unrestricted allocation of software functions to the edge, but lack real-time execution semantics and a real-time scheduling algorithm. In general, the allocation and scheduling of multiple constraint tasks in a distributed execution environment is classified as NP-complete. Nevertheless, by using prior knowledge, we are able to set up an optimal scheduling algorithm which leads to a highly reduced time complexity. Thus, our efficient approach enables modularity even for safety-critical real-time systems.