Trade-off analysis of real-time control performance and schedulability

Most real-time computer-controlled systems are developed in two separate st ages: controller design followed by its digital implementation. Computation al tasks that implement the control algorithms are usually scheduled by tre ating their execution times and periods as unchangeable parameters. Task sc hedulability therefore depends only on the limited computing resources avai lable. On the other hand, controller design is primarily based on the conti nuous-time dynamics of the physical system being controlled. The set of tas ks resulting from this controller design may not be schedulable with the li mited computing resources available. Even if the given set of tasks is sche dulable, their overall performance may not be optimal in the sense that the y do not make a full use of the computing resources. In this paper, we prop ose an integrated approach to controller design and task scheduling. Specif ically, task frequencies (or periods) are allowed to vary within a certain range as long as such changes do not affect critical control functions such as the maintenance of system stability. We present an algorithm that deter mines the task frequencies such that a prescribed aspect of system performa nce is optimized subject to satisfaction of computing resource constraints. The tasks are then scheduled with the chosen frequencies. The proposed app roach also addresses the issue of choosing controller processors.