A Fast Converging and Globally Optimized Approach for Load Balancing in Cloud Computing

Cloud Computing is the dynamic provisioning of resources to provide services end-users over internet. The realization cloud computing requires addressing several challenges, such as resource discovery, security, scheduling, and load balancing. Among these research issues, balancing most challenging one. Therefore, in past few years, into various static algorithms achieve optimal results gaining importance. This proposes Swarm Intelligence (SI) a load-balancing solution for computing. Several alternatives literature (like genetic algorithm, ACO, PSO, BAT, GWO, many others) are investigated, but none consider convergence time with global optimization. algorithms, this emphasizes Particle Optimization (PSO) Grey Wolf (GWO). A combined approach GWO-PSO that capitalizes on benefits fast optimization proposed paper. These two techniques enhance system efficiency allocation, working together solve challenge. Compared other traditional approaches, findings promising while achieving globally optimized reducing overall response time. On average, technique reduced 12% compared algorithms. Furthermore, best value obtained from objective function algorithm improves PSO 97.253% terms convergence.