Hard drive failure prediction using Decision Trees

Aiming at practical application of prediction models, we test the models on another real-world dataset with different drive models, on a real-world hybrid dataset with multiple drive models, and on several datasets containing fewer drives. Both prediction models show steady prediction performance, with high failure detection rates (80% to 96%) and low false alarm rates (0.006% to 0.31%). We also implement a reliability model for RAID-6 systems with proactive fault tolerance and show that the proposed models can significantly improve the reliability and/or reduce construction and maintenance cost of large-scale storage systems.