Machine Learning Algorithms for Automatic Anomalies Detection in Data Storage Systems Operation

Abstract

Data storage reliability and availability play important role for a wide range of services and business processes. Manufacturers provide data storage systems that resistant to hardware and software failures but not for all cases. Well-timed detection of these failures help to recover the system faster and prevent the failures before they occur. In this work a range of machine learning and time series analysis algorithms for failures detection is considered. The algorithms are applied and compared on the real data storage system. Preliminary results show that binary classification methods demonstrate high failure detection and low false alarm rates. Time series prediction based approach shows similar results and outperforms one-class classification methods.