Load Balancing in Cloud using improved GWO(iGWO)

The rapid increase of data computation and storage in cloud results in uneven distribution of workload on its heterogeneous resources, which may violate SLAs and degrades system performance. Distributing a balanced workload over the available hosts is a key challenge in a cloud computing environment. The main problem of using population-based meta-heuristic algorithms (like PSO, ABC, HS, etc.) is to properly tune their algorithm specific control parameters. The control parameters are sometimes problem specific and hence the performance of such algorithms is heavily dependent on their parameters. To alleviate the tuning of parameters, GWO is used to minimize the imbalance of cloud load. GWO is less dependent on their control parameters and powerful in terms of convergence, exploration, exploitation and local optima avoidance. In this Paper, meta-heuristic and based on Grey Wolf Optimization (GWO), which is an optimization technique inspired by hunting behavior of grey wolves. All the approaches optimize the degree of imbalance of cloud datacenter to improve system performance. The other approach is based on classical GWO. The fourth approach is the hybrid Grey Wolf Optimization-Particle Swarm Optimization (GWO-PSO) approach with the benefits to avoid trapping into local optima and to achieve global optima. The fifth approach is based on GWO with improvements (iGWO) to further improve the convergence using a right balance between exploration and exploitation phases.