Load balancing in cloud environment using enhanced migration and adjustment operator based monarch butterfly optimization

•The proposed work which is designed being a Meta-heuristic approach doesn't get struck into local optimum during the search process and to find an optimal solution.•Monarch Butterfly being a population based search performs the search process with random initial population and is enhanced over the course of time.•Being population based search, the proposed work can move into promising areas of search space thus the exploration rate is found to be greater when compared to single solution based search algorithms.•The shift in convergence is found to be uniformly maintained during the exploration and exploitation.•The major improvement of this approach the throughput, response time is found to improve and migration time, fault tolerance and energy consumption is found to be minimized when compared to the bench marks. In the decades before the advent of computers, humans tend to make mistakes while calculating and remembering tasks. Distributed computing helped to reduce the workload of each computer by distributing the workload evenly among computers connected in the network. Cloud computing have eradicated most of the problems that occurred in distributed computing but were also prone to different types of issues. Major issues in cloud computing relate to security and load balancing. Load balance of a node relates to two important parameters namely request time and response time. Meta heuristics algorithms can be used to provide proper load balancing techniques in cloud. This paper provides a mechanism namely EMAMBO to ensure that each node is properly load-balanced in cloud. Based on different metrics considered, it could be inferred that the proposed system fares better when compared to different benchmarked existing systems.