METHOD FOR VIRTUAL MACHINE SOFTWARE AGING PREDICTION BASED ON ADABOOST-ELMAN

摘要

The present invention provides a method for virtual machine software aging prediction based on AdaBoost-Elman, relating to the technical field of cloud computing. In the method, a level is first set for evaluating the extent of aging of virtual machine software, and a software aging index prediction model of the virtual machine and reference prediction model of an unaged virtual machine are trained; then a service concurrency prediction value and performance data are inputted into the software aging index prediction model of the virtual machine trained in the offline process and the reference prediction model of the unaged virtual machine; the software aging index prediction result of the virtual machine and the reference prediction result of the unaged virtual machine are outputted; finally, the software aging trend of the virtual machine is evaluated according to the software aging index prediction result of the virtual machine and the reference prediction result of the unaged virtual machine. The method of the present invention can predict the software aging index of a currently operating virtual machine and compare it with an unaged virtual machine so as to obtain the extent of software aging of the virtual machine in the subsequent next period of time, and take preventive measures in advance.