Large Scale Predictive Analytics for Hard Disk Remaining Useful Life Estimation

Abstract

Hard disk failure prediction plays an important role in reducing data center downtime and improving service reliability. In contrast to existing work of modeling the prediction problem as classification tasks, we aim to directly predict the remaining useful life (RUL) of hard disk drives. We experiment with two different types of machine learning methods: random forest and long short-term memory (LSTM) recurrent neural networks. The developed machine learning models are applied to predict RUL for a large number of hard disk drives. Preliminary experimental results indicate that random forest method using only the current snapshot of SMART attributes is comparable to or outperforms LSTM, which models historical temporal patterns of SMART sequences using a more sophisticated architecture.