A Virtual Machine Instance Anomaly Detection System for IaaS Cloud Computing

Abstract

Infrastructure as a Service (IaaS) is one of the three important fundamental service models provided by cloud computing. It provides users with computing resource and storage resource in terms of virtual machine instances. Because of the rapid development of cloud computing, more and more application systems have been deployed on the IaaS cloud computing platforms. Therefore, once anomalies incur in the IaaS cloud computing platforms, all the application systems cannot work normally. In order to enhance the dependability of IaaS cloud computing platform, a virtual machine instance anomaly detection system is proposed for IaaS cloud computing platform to detect virtual machine instances that exhibit abnormal behaviors. The proposed virtual machine instance system consists of four modules that are the data collection, the data transmission, the data storage, and the anomaly detection. In order to reduce the computing complexity and improve the detection precision, the anomaly detection module introduces the principal components analysis to reprocess the collected data and then adopts the Bayesian decision theory to detect the abnormal data. Experimental results show that the proposed virtual machine instance anomaly detection system is effective.