Artificial Gorilla Troop Optimization Based Load Balancing of Workflow Tasks in Cloud Environment

Abstract

Cloud computing is a popular technology that offers virtualized computer resources based on the internet. The performance utilization of the cloud resources depends mainly on the load-balanced resource allocation schemes. Load balancing is the distribution of the dynamic workload among cloud resources maintaining the load shares onto resources to ensure that no resource is overloaded or underloaded. Therefore, an efficient load-balancing strategy improves services and resource utilization. In this paper, an artificial gorilla troop optimization (GTO) based metaheuristic is proposed for load balancing of workflow tasks onto VMs in cloud systems. This method mimics the social behavior of the group of gorillas. The experimental results exhibit the superior performance of GTO on resource utilization than the PSO algorithm for the same objective and environment.