Efficient Task Scheduling in Cloud Computing using an Improved Particle Swarm Optimization Algorithm

Abstract

An improved multi-objective discrete particle swarm optimization (IMODPSO) algorithm is proposed to solve the task scheduling and resource allocation problem for scientific workflows in cloud computing. First, we use a strategy to limit the velocity of particles and adopt a discrete position updating equation to solve the multi-objective time and cost optimization model. Second, we adopt a Gaussian mutation operation to update the personal best position and the external archive, which can retain the diversity and convergence accuracy of Pareto optimal solutions. Finally, the computational complexity of IMODPSO is compared with three other state-of-the-art algorithms. We validate the computational speed, the number of solutions found and the generational distance of IMODPSO and find that the new algorithm outperforms the three other algorithms with respect to all three metrics.