A Density-Based Anomaly Detection Method for MapReduce

Cloud computing has been more and more popular and widely used as a new model of information technology. In order to achieve a reliable and efficient operation of the cloud environment, it is important for cloud providers to detect and deal with system anomalies in time. In this paper, we present a method for anomaly detection in MapReduce environment. This method is based on peer-similarity and uses density based clustering on OS-level metrics to perform real time analysis. The peer-similarity as well as our anomaly detection method is evaluated through experiments. Compared with other methods, the method proposed in this paper reflects the characteristics of simple, sensitive and efficient. And it can be deployed in both online and offline environment.