Multi-objective energy aware task scheduling using Orthogonal Learning Particle Swarm Optimization on cloud environment

Cloud computing provides Internet users with access to services and shared resources through service providers. But efficient task scheduling on cloud is one of the most important research issues to focus. This is because task scheduling is difficult and complicated when taking into account energy consumption, processing cost and cloud datacentre’s task completion time. To overcome these, an appropriate task scheduling strategy for providing effective executions in cloud environment is essential. Therefore, a Multi-objective energy aware task scheduling using Orthogonal Learning Particle Swarm Optimization (OLPSO) is proposed. Orthogonal learning is modified with PSO to improve convergence accuracy and increase convergence speed. Also the multi-objective function is designed based on execution time, energy consumption and processing cost. Different measures are used to examine and compare the performance of the suggested technique with other algorithms namely, orthogonal learning with grey wolf optimization (OLGWO) and orthogonal learning with genetic algorithm (OLGA).