A New Method for Scheduling Load Balancing in Multi-processor Systems Based on PSO

Abstract

In parallel and distributed systems, optimal task scheduling and load balancing has always been of great interest in order to minimize the time and speed up the process which plays a major role in the efficiency of such systems. By load balancing we mean scheduling the jobs in a way that every job could be executed concurrently while it is mapped to a processing unit, such as a processor (in a multi-processor system) or a computer (in a grid computer). It has been proved that dynamic load balancing is an NP-complete problem and designing an optimal scheduler that increases the efficiency and speed of the parallel systems is desired. In this paper, we want to present an algorithm for task scheduling and load balancing in multi-processor systems based on PSO method that can minimize the maximum span and average utilization of all processors in an optimal way.