A hybrid elephant herding optimization and harmony search algorithm for potential load balancing in cloud environments

Abstract

In cloud computing environment, load balancing delinquent arises when a large count of new IoT user requests are linked with specific fog nodes. So, a well-organized load balancing tactic is needed in cloud computing. Therefore, in this manuscript, a hybrid elephant herding optimization and harmony search algorithm (HSA) for potential load balancing in cloud environments (HEHO-HSA-PLB-CE) is effectively proposed for reducing task waiting time, load balancing rate, scheduling time, delay and energy consumption. The HEHO algorithm and HSA are mainly used for leveraging the allocation of virtual machine (VM) and incorporating an enhanced strategy of physical machine selection. The proposed HEHO-HSA-PLB-CE method aims at preventing the issue of premature convergence or the issue related to the solution falling at the point of local optimum. Finally, the proposed method potentially achieves load balance under the allocation of VM and enhancement of resource utilization in the cloud computing environment. The proposed approach is activated in CloudSim and the efficiency of the proposed method is assessed by evaluation metrics, such as response time, load balance rate, scheduling time, delay, energy consumption. Then, the simulation performance of the proposed method provides lower delay 32.82%, 25.32%, 29.34% and 34.18%, low energy consumption 38.22%, 25.46%, 42.12% and 15.34% compared with the existing methods, like Aquila optimizer for PLB in CE (AO-PLB-CE), arithmetic optimization algorithm for PLB in CE (AOA-PLB-CE), sine cosine algorithm for PLB in CE (SCA-PLB-CE), and enhanced krill herd algorithm for PLB in CE (EKHO-PLB-CE) respectively.