Scheduling Tasks in a Real-Time System

Abstract : A heuristic technique for dynamically scheduling tasks in a real-time system is described in this paper. Each task is defined by a begin time, a deadline and a required computation time. The scheduling problem is to schedule every task successfully, i.e., each task should start after its begin time and complete its execution before its deadline. Two characteristics distinguish our task model and heuristic technique: First, a new task to be scheduled is allowed to modify a previous, partial schedule that is already feasible. Thus, the heuristic technique can be used either to build a feasible schedule from scratch or extend a partial, feasible schedule. Second, each task is bounded by a window of time defined by the begin and end times. The begin time is typically equal to or greater than the task arrival time. The end time is typically equal to or less than the task deadline. The additional constraint of starting a task after specified time instant is useful in task synchronization. Comparisons with known heuristic techniques for dynamically scheduling tasks in a real-time system are made via simulation. The results show that the proposed approach has a higher degree of success in obtaining a feasible schedule compared to the other approaches.