DAC‐Hmm: detecting anomaly in cloud systems with hidden Markov models
Bin Hong, Fuyang Peng, Bo Deng, Yazhou Hu, Dongxia Wang · Concurrency and Computation Practice and Experience · 2015
Summary Cloud computing has rapidly been adopted in recent years by freeing users from the low‐level task of setting up the hardware and managing the system software. Anomaly detection is an effective approach to enhancing availability and reliability of Cloud infrastructures. Anomaly detection solution for Cloud computing systems must operate at runtime and without the need for prior knowledge about normal or anomalous behaviors. In this paper, we propose an unsupervised online anomaly detection scheme based on hidden Markov Model. Our algorithm is basically distributed and runs locally on each computing machine on the Cloud in order to achieve high scalability. Experiments performed on real data sets validate the fact that our algorithm can achieve high detection accuracy for a range of system anomalies with low overhead to the infrastructure in Cloud. Copyright © 2015 John Wiley & Sons, Ltd.