Attention-Based Bidirectional LSTM With Differential Features For Disk RUL Prediction

With the rapid growth in the number of disks, disk failures are increasingly becoming a problem for data centers. To improve the reliability and security of the data center, deep learning methods have been widely used by performing the remaining useful life (RUL) prediction of hard disk drives (HDD). However, deep learning methods fail to deal with the long sequence data and extract the crucial degradation information. In this paper, an attention-based bidirectional long short-term memory (LSTM) with differential features method is proposed, in which the differential features are extracted by manual feature engineering, and then apply the attention-based bidirectional LSTM network to assign higher weights to crucial features that contain useful degradation information for RUL prediction. Experiments results on the Backblaze dataset show that the proposed approach outperforms the traditional LSTM methods, and achieves a 97.83% failure detection rate (FDR) to predict RUL of HDDs up to 60 days before failure.