With the rapid deployment of cloud platforms, high service reliability is of critical importance. An industrial cloud platform contains a huge number of disks and disk failure is a common cause of service unreliability. In recent years, many machine learning based disk failure prediction approaches have been proposed, which can predict disk failures based on disk status data before the failures actually happen. In this way, proactive actions can be taken in advance to improve service reliability. However, existing approaches treat each disk individually and do not explore the influence of the neighboring disks. In this paper, we propose Neighborhood-Temporal Attention Model (NTAM), a novel deep learning based approach to disk failure prediction. When predicting whether or not a disk will fail in near future, NTAM is a novel approach that not only utilizes a disk’s own status data, but also considers its neighbors’ status data. Moreover, NTAM includes a novel attention-based temporal component to capture the temporal nature of the disk status data. Besides, we propose a data enhancement method, called Temporal Progressive Sampling (TPS), to handle the extreme data imbalance issue. We evaluate NTAM on a public dataset as well as two industrial datasets collected from around 9 million of disks in an industrial public cloud platform. Our experimental results show that NTAM significantly outperform state- of-the-art competitors. Also, our empirical evaluations indicate the effectiveness of the neighborhood-ware component and the temporal component underlying NTAM and the effectiveness of TPS. More encouragingly, we have successfully applied NTAM and TPS to Company M’s public cloud platform and obtained practical benefits in industrial practice.

The Web Conference is announcing latest news and developments biweekly or on a monthly basis. We respect The General Data Protection Regulation 2016/679.