Comparison of Genetic Algorithm, Particle Swarm Optimization and improved Ant Colony Optimization for Scheduling of Heterogeneous Systems

Abstract

Heterogeneous systems scheduling is one of the important tasks in the field of parallel computing systems. Load partitioning is one of the effective solutions for this problem. Developing a heuristic algorithm gives better results for scheduling on this system. In this paper, we propose a hyper-heuristic scheduling algorithm based on a genetic algorithm and modified ant bee colony algorithm. An optimal model is developed to determine the number of load fractions, number of rounds in multiple processor systems. First, the best candidate solutions from the population are determined. Many heuristic algorithms like genetic algorithms and PSO are applied to find the optimal activation order of the heterogeneous systems. The improved particle swarm optimization and ant colony optimization is applied to find the optimum load fraction. The Simulation results show the comparison of performance in terms of standard deviation, mean, throughput and execution time.