On Self-triggered Full-Information H-Infinity Controllers

A self-triggered control task is one in which the task determines its next release time. It has been conjectured that self-triggering can relax the requirements on a real-time scheduler while maintaining application (i.e. control system) performance. This paper presents preliminary results supporting that conjecture for a self-triggered real-time system implementing full-information H∞ controllers. Release times are selected to enforce upper bounds on the induced L2 gain of a linear feedback control system. These release times are treated as requests by the system scheduler, which then assigns actual release times using Buttazzo’s elastic scheduling algorithm. Preliminary experimental results from a Matlab stateflow simulink model demonstrated a remarkable robustness to scheduling delays induced by real-time schedulers. These results show that self-triggered controllers are indeed able to maintain acceptable levels of application performance during prolonged periods of processor overloading.