SmartPred: Unsupervised Hard Disk Failure Detection
- Due to the rapidly increasing storage consumption worldwide, as well as the expectation of continuous availability of information, the complexity of administration in today’s data centers is growing permanently. Integrated techniques for monitoring hard disks can increase the reliability of storage systems. However, these techniques often lack intelligent data analysis to perform predictiveDue to the rapidly increasing storage consumption worldwide, as well as the expectation of continuous availability of information, the complexity of administration in today’s data centers is growing permanently. Integrated techniques for monitoring hard disks can increase the reliability of storage systems. However, these techniques often lack intelligent data analysis to perform predictive maintenance. To solve this problem, machine learning algorithms can be used to detect potential failures in advance and prevent them. In this paper, an unsupervised model for predicting hard disk failures based on Isolation Forest is proposed. Consequently, a method is presented that can deal with the highly imbalanced datasets, as the experiment on the Backblaze benchmark dataset demonstrates.…
Document Type: | Conference Proceeding |
---|---|
Conference Type: | Konferenzartikel |
Zitierlink: | https://opus.hs-offenburg.de/4407 | Bibliografische Angaben |
Title (English): | SmartPred: Unsupervised Hard Disk Failure Detection |
Conference: | ISC High Performance 2020 International Workshops, June 21-25, 2020, Frankfurt, Germany |
Author: | Janis KeuperStaff MemberORCiDGND, Philipp Rombach |
Year of Publication: | 2020 |
Place of publication: | Cham |
Publisher: | Springer |
Page Number: | 12 |
First Page: | 235 |
Last Page: | 246 |
Parent Title (English): | High Performance Computing |
Editor: | Heike Jagode, Hartwig Anzt, Guido Juckeland, Hatem Ltaief |
ISBN: | 978-3-030-59850-1 (Print) |
ISBN: | 978-3-030-59851-8 (eBook) |
DOI: | https://doi.org/10.1007/978-3-030-59851-8_15 |
Language: | English | Inhaltliche Informationen |
Institutes: | Fakultät Elektrotechnik, Medizintechnik und Informatik (EMI) (ab 04/2019) |
Forschung / IMLA - Institute for Machine Learning and Analytics | |
Institutes: | Bibliografie |
DDC classes: | 000 Allgemeines, Informatik, Informationswissenschaft / 000 Allgemeines, Wissenschaft / 004 Informatik | Formale Angaben |
Open Access: | Closed Access |
Licence (German): | Urheberrechtlich geschützt |