An Approach Based on Genetic and Grasshopper Optimization Algorithms for Dynamic Load Balancing in CloudIoT

CloudIoT is a new paradigm, which has emerged as result of the combination Cloud Computing (CC) and Internet Things (IoT). It experienced growing rapid development, it become more popular in information technology (IT) environments because advantages offers. However, due to strong use this especially smart cities, problem imbalance load emerged. Indeed, satisfy needs user, intelligent objects send collected data virtual machines (VMs) cloud order be processed. So, necessary have an idea about its VM. Thus, balancing between VMs strongly related technique used for selection. To tackle problem, we propose paper task scheduler called Scheduler Genetic Grasshopper Algorithm (SGGA). allows ensure dynamic balancing, well optimization makespan resource usage. Our proposed SGGA based on (GA) Optimization (GOA). First, tasks sent by IoTs are mapped build initial population, then performs genetic algorithm, expressed considerable performance. weakness GA marked heaviness caused mutation operator, when number increases. Because insufficiency, replaced operator with grasshopper algorithm. The results experiments show that our approach (SGGA) most efficient, compared recent approaches, terms response time obtain optimal solution, makespan, throughput, average utilization rate hypervolume indicator.