Prediction of Virtual Machine State Based on BP Neural Network

Abstract

Monitoring software for kernel-level rootkit malware in the cloud computing environment has been relatively perfect. However, these monitors can only ensure the security of virtual machines in the cloud environment, but cannot make a more accurate judgment on the future state of virtual machines. Kernel virtual machine for cloud computing environment safety status of prediction is affected by the impact factors of nonlinear, the traditional forecasting model is based on statistical methods, although dynamic allocation model can be used for the prediction, t the ability to overcome the non-linear influence is poorer, predicted results already can not meet the accuracy requirement of the Internet of things. In order to more accurately predict the cloud computing environment of virtual machine core security status in the future, based on the BP neural network in the virtual machine future state prediction model, and through factor analysis and factor analysis results normalized processing to reduce the size of the input data of BP neural network, the neural and network prediction time. Finally, by processing and simulating the data obtained by libvirt program, the feasibility of the model is verified. It can be seen that the model has a good prediction effect on the future state of the virtual machine.