A Framework for Designing Embedded Real-Time Controllers

Control systems are typically designed assuming all ideal behavior of the computing infrastructure where controllers execute. In practice, however in highly loaded computing systems consisting of multiple concurrent controllers, resource constraints may introduce delays and jitter in control loops that may degrade control performance significantly. Hence, taking resource constraints into account since the beginning of the design cycle is crucial for optimizing the performance of a control system. In this paper we propose a general framework for evaluating the performance of a control system as a function of multiple timing attributes (e.g., sampling frequencies, delays and jitter) and for selecting the proper control task parameters (e.g., periods and deadlines) taking resource constraints into account. The proposed framework is illustrated using a real control plant.