A virtual machine software aging prediction method based on adaboost-elman

Abstract

The invention provides a virtual machine software aging prediction method based on AdaBoost-Elman, and relates to the technical field of cloud computing. This method first sets the level for evaluating the aging degree of the virtual machine software, and trains the software aging index prediction model of the virtual machine and the reference prediction model of the non-aging virtual machine; In the software aging index prediction model of the virtual machine and the non-aging virtual machine reference prediction model, the software aging index prediction result of the virtual machine and the reference prediction result of the non-aging virtual machine are output; finally, according to the software aging index prediction result of the virtual machine and the non-aging virtual machine Evaluate the software aging trend of the virtual machine based on the reference prediction results of the virtual machine. The method of the invention can predict the software aging index of the current working virtual machine, and compare it with the non-aging virtual machine, so as to obtain the software aging degree of the virtual machine in the next period, and take preventive measures in advance.

Description

technical field [0001] The invention belongs to the technical field of cloud computing, and relates to an AdaBoost-Elman-based virtual machine software aging prediction method. Background technique [0002] In the cloud service system, virtual machines process concurrent business requests for a long time without interruption, and software aging will gradually occur, resulting in interruption or even failure of cloud services. In order to ensure the performance and reliability of cloud services, it is usually restarted before the virtual machine service fails to restore the initial state of the virtual machine application and system. The prediction of software aging trend is the key to solve the problem of virtual machine software aging. If measures are taken too early, the restart cost will be high, which will cause waste of resources; if measures are taken too late, it will not achieve the effect of reducing losses. [0003] The software aging of the virtual machine is a l...

AI Technical Summary

Problems solved by technology

However, this single threshold monitoring method cannot accurately represent the "health status" of the virtual machine, and is often affected by external loads, resulting in misjudgment

[0004] In the cloud service system, the software aging of virtual machines is ultimately caused by a large number of business requests. However, the existing software aging prediction methods often directly fit the historical sequence of virtual machine For business considerations, all businesses share virtual machine resources, and different business requests require different resource types and resource quantities. The previous methods have errors in directly fitting the software aging indicators of virtual machines.

Images