Load balancing in cloud using improved gray wolf optimizer

Abstract Cloud computing allocates virtual resources dynamically on user's demand. The sudden rise of data storage and computation in the cloud computing environment may cause an imbalanced workload distribution. As a result, job completion time will be higher in overloaded servers than the underloaded servers in the same environment. Distributing load fairly in the cloud is a crucial challenge. Traditionally, load balancing is used to distribute the workload among multiple servers to overcome the overloading and underloading of servers. This article presents a novel load balancing approach for cloud computing using improved gray wolf optimization algorithm. We compare our approach with harmony search algorithm, artificial bee colony algorithm, particle swarm optimization, and gray wolf optimization algorithms. Results of simulation are encouraging with improved system performance and fair utilization of resources.