An Evolutionary Fuzzy based Scheduling Algorithm for Soft Real-Time Multiprocessor Systems

Scheduling algorithms are designed to ensure high level of performance for real-time systems by optimizing the allocation of resources and time to tasks thus meeting specific system requirements. The task scheduling problem is known to be NP-Complete and is not simply solved. This paper proposes a novel scheduling algorithm for real-time systems using two fuzzy inference engines. The results of the proposed algorithm are compared with those of the two existing scheduling algorithms which are the Earliest Deadline First and Least Laxity First scheduling algorithms. The scope of this paper is limited to the non-preemptive independent tasks for a multiprocessor environment.