Multi-criteria scheduling of soft real-time tasks on uniform multiprocessors using fuzzy inference

Abstract

Scheduling algorithms play an important role in design of real-time systems. Due to high processing power and low price of multiprocessors, real-time scheduling in such systems is more interesting, yet more complicated. Uniform multiprocessor platforms consist of different processors with different speed or processing capacity. In such systems the same piece of code may require different amount of time to execute upon different processing units. It has been proved that there in no optimal online scheduler for uniform parallel machines. In this paper a new fuzzy-based algorithm for scheduling soft real-time tasks on uniform multiprocessors is presented. The performance of this algorithm is then compared with that of EDF algorithm. It is shown than our proposed approach has supremacy over EDF in some aspects, since it usually results in higher success ratio, better utilizes the processors and makes a more balanced schedule. © 2007 Springer.