Certain investigations on particle swarm optimization techniques for multiprocessor scheduling

Abstract

The present research focuses on Particle Swarm Optimization and its variant approaches for multiprocessor static and dynamic task scheduling problem Scheduling in a multiprocessor architecture has increased in the past decades due to the changing markets characterized by global competition and rapid development of new processes and technologies Two types of newlinemultiprocessor task scheduling are Static Task Scheduling and Dynamic Task Scheduling Static Task Scheduling requires prior knowledge of its execution time on the processing nodes Dynamic Task Scheduling does not require knowledge about the execution time of the tasks to be scheduled The concepts of PSO and its variants are successfully tested with static independent tasks and dynamic tasks with load balancing and without load balancing in a multiprocessor architecture to reduce the makespan of the entire schedule The static and dynamic tasks considered for scheduling in the present research are non preemptive in nature newline newline