DPSO: A Hybrid Approach for Load Balancing using Dragonfly and PSO Algorithm in Cloud Computing Environment

Abstract

Load balancing is one of the promising challenges in cloud computing system. For solving the issues, many heuristic, meta heuristic, evolutionary and hybrid algorithms have been proposed by the researchers. Still, it is under way of research for finding optimal solution in dynamic change in behaviour of task as well as computing environments. Attempts have been made to develop a hybrid framework to balance the load in cloud environment by obtain the best fitness value. To achieve an optimal resource for load balancing, the proposed framework integrates Dragonfly (DF) and Particle Swarm Optimization (PSO) algorithm. The performance of the proposed method is compared with PSO and Dragonfly algorithm. The performance is evaluated in different measures such as best fitness value, response time by varying the user base and response time. The user bases are varied from 50, 100, 500, and 1000. Similarly, the population size has been varied to observe the performance of the algorithm. It is observed that the proposed method outperforms the other approached for load balancing. The statistical analysis and standard testing also validate the relative superiority of PSO a considerable Dragonfly Algorithm. The hybrid approach provides better response time.