Fire Hawk Optimization based Multi-objective Dynamic Load Balancing in Cloud Computing

Load Balancing (LB) of the tasks on Cloud Computing (CC) is the significant characteristics of distribution of the resources from data center. LB has to be taken out in such a way that every Virtual Machines (VMs) must have balanced the load to attain an optimal utilization of its capabilities. As an outcome, the LB of tasks on VM is examined as a significant thing of task scheduling in the cloud. The LB in cloud faced various challenges like fault tolerance as well as data security. In this research, Fire Hawk Optimization (FHO) algorithm is proposed for the dynamic LB in cloud environment. The aim of this research is to enhance the system performance and it considers the multi-objective functions named Makespan, Resource Utilization (RU), Response Time (RT), Degree of Imbalance as well as throughput. The experimental results proven that the proposed FHO-based LB had obtained the 2246, 6.7, 134.23, 141 and 5.5 in the number of tasks of 1500 using nakespan, RT, RU, DOI and throughput. These results show better enhancement when compared to the previous approaches like Particle Swarm Optimization (PSO), Q-learning Modified PSO (QMPSO) and Binary JAYA algorithm.