To improve the performance on disk load balancing in a cloud environment using improved Lion optimization with min-max algorithm

Abstract

A key challenge was optimizing the speed of the network while maintaining impartiality. Power monitoring solutions have been developed to reduce these load imbalances. These techniques frequently need unique hardware or software on the participants' end. To accomplish the cloud computing system of load balancing, this study created an intelligent virtual machine programming scheme using a machine learning technique. The researchers introduced two methods that identify optimal probabilistic solutions to the issue after conducting an in-depth investigation. A min-max load balancing solution is generated by the second method, while the first approach reduces the load on the network's crowded Access Points (APs). Let's focus on the mapping of links in particular because the mapping of nodes was established a priori. This study provides an innovative and effective Improved Lion Optimization (ILO) with Min-Max Algorithm for enabling VNE in real systems consisting, breaking new ground in the research to employ Genetic Operators for parallelization. Load balancing & power conservation were two crucial goals that must be taken into account, and also the findings reduce the cost of processing time, the proposed system outperforms the sequentially one in terms of both goals. In addition, the adaptive capacity of the proposed algorithm was assessed across various substrate structural configurations. The load balancing goal was achieved; the typical data center usage was higher than that of other methods, reaching nearly 80%; the largest amount of virtual machine migration was reduced by 94.5%; the data center's maximum energy consumption was reduced by 49.13%.