Abstract
Failure prediction for hard disk drives is a typical and effective approach to improve the reliability of storage systems. In a large-scale data center environment, the various brands and models of drives serve diverse applications with different input/output workload patterns, and non-ignorable differences exist in each type of drive failures, which make this mechanism much challenging. Although many efforts are devoted to this mechanism, the accuracy still needs to be improved. In this article, we propose a failure prediction method for hard disk drives based on a part-voting random forest, which differentiates prediction of failures in a coarse-grained manner. We conduct groups of validation experiments on two real-world datasets, which contain the SMART data of 64,193 drives. The experimental results show that our proposed method can achieve a better prediction accuracy than state-of-the-art methods.
Highlights
Large-scale storage systems are widely used in many sites, including high-performance computing systems and Internet service providers.[1]
We propose a differential failure prediction method based on a random forest and a clustering algorithm
Our experimental datasets are acquired from two different sources; one dataset is from the data center of Baidu,[32] and the other dataset is from the storage system of Backblaze.[33]
Summary
Large-scale storage systems are widely used in many sites, including high-performance computing systems and Internet service providers.[1]. The disastrous consequences of HDD failures can be permanent and difficult to be recovered, even unrecoverable, which leads to longer server down time and lower reliability of Internet data centers (IDCs).[2,3,4] To ensure the reliability and stability of systems, IDCs monitor the working conditions of HDDs in real time to detect soon-to-fail HDDs by sensors,[5,6,7] including accelerometers and acoustic emission sensors, thermal sensors, and counters Accuracy of these approaches is not promising. Wear-out failure exhibits a much longer deterioration process than the other types of failure and is easier to predict
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: International Journal of Distributed Sensor Networks
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
