A multi-instance LSTM network for failure detection of hard disk drives

Abstract

Hard disk (HDD) failure is the most important reliability issue in the data center. Therefore, the prediction of hard disk failure has become the focus of attention of major data centers. However, most current research work does not notice the fact that the data on the hard disk is mostly unlabeled data. Since the degradation period in HDD is very short, the mixture of health data and erroneous data can cause serious data imbalance. This makes fault prediction a difficult task. In response to the above problems, a multi-instance long-term sequence classification method based on long-short-term memory (LSTM) network is proposed. By dividing the longterm sequence data packet into multiple instances, the relationship between the instance and the sample label is studied to predict HDD failure. Through the analysis of the hard disk data of a communication company and the Backblaze data center, this method can obtain better results than other methods.