Research on Algorithm of Dependability Oriented Anomaly Detection of Virtual Machines under Cloud

摘要

In this paper, a large-scale cloud platform Virtual machine anomaly detection key technologies. For cloud environments systematic study of the feature extraction technique is proposed based on principal component analysis (PCA) for feature extraction algorithm. The algorithm selects the most efficient or concentrated extract from the original performance, data analysis most useful "features", the first analysis of the anomaly detection problem to be solved.