Dynamic value-density for scheduling real-time systems

Scheduling decisions in time-critical systems are very difficult, due to the vast number of systems’ parameters and tasks’ attributes involved in such decisions. Due to the intractability of the problem, time-critical systems often have to resort to heuristic techniques. Value-based scheduling heuristics have been found in the literature to experience a more graceful degradation under overload situations than various other heuristics. However, value-based scheduling heuristics found in the literature combine the tasks’ significance with some of the tasks’ static attributes, and therefore, they derive fixed scheduling priorities. In this study, we propose value-based scheduling heuristics that combine the tasks’ significance with some of the tasks’ dynamic attributes to derive dynamic scheduling priorities, in order to enhance the overall system’s performance under normal operating loads and to reduce any performance degradation due to overload situations.