An Efficient Load Balancing Method by Using Machine Learning-Based VM Distribution and Dynamic Resource Mapping

Abstract

In cloud computing, balancing the load among VMs and resources is a major research area, which still needs attention. The primary aim of this research is to expand an effective cloud load balancing approach, enhance the reaction time, lessen the ready time, premiere utilization of sources as well lessen the activity rejection time. The proposed MLBL method is primarily based on the SVM and K suggest clustering method. In the proposed MLBL technique SVM classification method used to create activity businesses based totally at the size. Later K method clustering technique is used to create the institution of Virtual machines based totally on their usage of CPU and number one memory (RAM). We are providing an MLBL method based totally on system learning-based VM distribution and dynamic aid mapping. In cloud computing, VMs are scheduled to hosts as in keeping with their utilization (a host which has better availability of memory) without thinking about common utilizations. The proposed technique divides the assets into various organizations as well as VMs and then follow dynamic aid mapping. The proposed MLBL technique creates VMs clusters to execute comparable task agencies that enhance the QoS and ideal utilization of sources in addition to lessen the process rejection time.