Virtual machine monitoring method in vector-autoregression-based cloud computing

Abstract

The invention relates to a virtual machine monitoring method in vector-autoregression-based cloud computing, which is a novel monitoring method. Because the data volume of specific monitoring of virtual machine monitoring in cloud computing is relatively huge, a huge pressure is caused to a monitoring system by the adoption of periodic monitoring, the monitoring in a 'pull' mode, through which more resources are saved, is adopted, but the intelligent judgment on the time for collecting the data is decided, therefore, not only the real-time capability is increased, but also the resource pressure of the system is reduced; the real-time monitoring is realized based on the virtual machine monitoring in the cloud computing based on VAR (vector autoregression), and the use ratio of the resource is improved. A new regression equation can be established by a model according to the original data model, prediction is made to the resource data in the next period, and the collection of the analog data is carried out according to the prediction values and the cooperation with the 'pull' mode. The self-adaption and the real-time capability of the resource monitoring are increased by the algorithm.

Description

technical field [0001] The invention is a resource monitoring method of a virtual machine in cloud computing. The method predicts resource changes based on a vector autoregressive model, and solves the problem of how to determine the polling time when monitoring virtual machine resources in cloud computing. The invention belongs to distributed computing and cloud computing technologies. Background technique [0002] Cloud computing is a new Internet computing model, through which the on-demand sharing of software and hardware resources and information in the network is realized. [0003] Cloud computing is widely believed to be another sea change lagging behind the big shift from mainframe computers to the client-server computing paradigm. Users no longer need to understand the details of the infrastructure in the "cloud" and do not need to directly control it. Cloud computing describes a new Internet-based IT service growth, consumption and delivery model, usually involvi...

AI Technical Summary

Problems solved by technology

This method solves the problems of high load caused by too dense fixed periodic monitoring in the virtual machine monitoring system in cloud computing, system overhead and poor real-time performance caused by too sparse fixed periodic monitoring

Images