Control-performance-driven period and deadline selection for cyber-physical systems

Control performance improvement of cyber-physical systems (CPS) can be achieved by optimizing period and deadline parameters of controller tasks. It is challenging due to the tight coupling between periods and deadlines of tasks caused by system schedulability constraints. To handle the coupling within the parameter selection problem, this paper presents an approximation algorithm to make synchronous period and deadline adjustment with system schedulability guarantees. Experimental results demonstrate that the proposed method is robust for different workload situations and outperforms existing methods for systems consisting of many delay-aware controller tasks.