A Two-Step Parametric Method for Failure Prediction in Hard Disk Drives

• Published in: IEEE transactions on industrial informatics 2014-02, Vol.10 (1), p.419-430
• Main Authors: Wang, Yu, Ma, Eden W. M., Chow, Tommy W. S., Tsui, Kwok-Leung
• Format: Article
• Language: English
• Subjects: Anomalies; Anomaly detection; Cost function; Disk drives; Failure; failure prediction; False alarms; generalized likelihood ratio test; hard disk drive (HDD); Hard disks; Hidden Markov models; Indexes; Prediction algorithms; Predictive models; Support vector machines
• ISSN: 1551-3203; 1941-0050
• DOI: 10.1109/TII.2013.2264060

Predicting the impending failure of hard disk drives (HDDs) is crucial for preventing essential data from losing. In this paper, a two-step parametric method was developed to predict the impending failure of HDDs using the aggregate of statistical models. This method deals with the problem of failure prediction in two steps: anomaly detection and failure prediction. First, Mahalanobis distance was used for aggregating all the monitored variables into one index, which was then transformed into Gaussian variables by Box-Cox transformation. By defining an appropriate threshold, anomalies in HDDs were detected as a result. Second, a sliding-window-based generalized likelihood ratio test was proposed to track the anomaly progression in an HDD. When the occurrence of anomalies in a time interval is found to be statistically significant, indicating the HDD is approaching failure. In this work, we also derived a new cost function to adjust the prediction rate. This is important in a way to balance the failure detection rate and false alarm rate as well as to provide an advanced warning of HDD failures to the users, whereby the users can back up their data in time. Then the developed method was applied on a synthetic data set showing its effectiveness on predicting failures. To demonstrate the practical usefulness, this method was also applied on a real-life HDD data set. The result shows that our method could achieve 68% failure detection rate with 0% false alarm rate. This is much better than the results achieved by the state-of-the-art methods, such as support vector machine and hidden Markov models.