Analysis and investigation of task allocation to virtual machine resources for load balancing in cloud computing based on various machine learning classifiers

Load balancing is an important aspect in the field of cloud computing to increase workload distribution and efficient resource utilization, which in turn reduces the overall system response time. Many approaches and algorithms have been proposed to solve load balancing problems such as task scheduling, migration, resource utilization, etc. This study presents several approaches related to the critical challenge in cloud computing, which is load balancing. The problems related to load balancing are discussed through a comparative analysis of the algorithms proposed by researchers in the last six years. Several approaches have been proposed, however, there are still some issues in the cloud environment, such as virtual machine migration, fault tolerance issues that have not been fully resolved yet. In this study, an improved virtual machine classification model is presented for workload balancing in cloud computing applications using deep neural networks and evolutionary weeding algorithm. In fact, the main objective of the study is to optimize the use of computing resources in the cloud environment, where scheduling algorithms play an important role in the optimization process. In fact, the proposed topic is in the field of machine learning and virtual machine classification for load balancing in cloud computing. In the simulation of the proposed method, in the evaluation of the comparison of the proposed method and the base method in terms of the accuracy of the assignments, the proposed method has recorded an improvement of 6.6 percent compared to the base method.