AN ANOMALY DETECTION METHOD FOR THE VIRTUAL MACHINES IN A CLOUD SYSTEM

摘要

This invention relates to an anomaly detection method for the virtual machines in a cloud system, in which an HsMM is trained by searching the state information of the normal virtual machines in the cloud system, and a corresponding algorithm is designed to detect and calculate the probabilistic logarithm probability and the Mahalanobis distance of the dynamic changing behaviors of the resources in the cloud system when each virtual machine is online. If the Mahalanobis distance value of an online virtual machine is detected being higher than the preset threshold value of the cloud system, it is suggested that the virtual machine is operating anomalously. Moreover, an anomaly detection and treatment system in the cloud system will start to detect and treat the anomaly of the virtual machine. Furthermore, if the anomaly rate of a virtual machine is detected being lower than the maximum threshold value of the anomaly detection and treatment system, the system will remove the anomaly and issue warnings to the corresponding cloud renter; otherwise, the system will issue warnings to the corresponding cloud renter and shut down the virtual machine. Therefore, compared with traditional anomaly detection method, this invention can detect anomalous behaviors of the virtual machines in a cloud system in real time, occupying less cloud system resources, with adequately high availability and security for the virtual machines in the cloud system.