Hybrid genetic algorithm for task scheduling in distributed real-time system

Abstract

A distributed real-time system consists of a set of heterogeneous processors located at possibly different sites and connected by a communication link. Task scheduling in distributed real-time system attracts the attention of the researcher in many disciplines. Many researchers have been developed the solution of task scheduling problem by using different types of technique. In this paper, a hybrid genetic algorithm (HGA) is developed which is a combination of k-means and genetic algorithm to form the clusters of tasks in an effort to minimise the communication costs. A genetic algorithm is also developed to schedule the formed clusters of tasks onto set of processors to minimise the execution costs. The results of the algorithm have been compared with various existing techniques. Experiment results shows that the proposed algorithm achieves better efficiency than other existing techniques.