Maximizing Real-Time System Utilization by Adjusting Task Computation Times

A real-time system is any information processing system that has to respond to externally generated input stimuli within a finite and specified period: the correctness depends not only on the logical result but also on the time it was delivered; the failure to respond is as bad as the wrong response [1]. Real-time systems can be constructed out of sequential programs but are typically built from concurrent programs called tasks. A real-time task is an executable entity of work that, at a minimum, is characterized by the worst-case execution time (WCET) [2] and time constraints [3]. The WCET is estimated as the maximal time required by the processor to execute the task. A typical timing constraint of a real-time task is the deadline, which is defined as the maximal completion time of a task without causing any damage to the system [4–6]. There are two main classes of real-time system: (1) hard and (2) soft real-time systems. The hard real-time must meet its deadlines. In case of failure, its operation is without value and the system for which it is a component is of no use. Embedded systems are often hard real-time systems. Such systems have practical applications 1