Explore deep auto-coder and big data learning to hard drive failure prediction: a two-level semi-supervised model
Predicting impending failure of hard disk drives (HDDs) is crucial to avoid losing essential data and service downtime. However, most HDD failure prediction is being challenged by using labelled data itself to evaluate failure rate, while the fact that HDDs deteriorate gradually cannot be described...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Taylor & Francis Group
2022-12-01
|
Series: | Connection Science |
Subjects: | |
Online Access: | http://dx.doi.org/10.1080/09540091.2021.2008320 |
_version_ | 1797684052967292928 |
---|---|
author | Yan Ding Yunan Zhai Yujuan Zhai Jia Zhao |
author_facet | Yan Ding Yunan Zhai Yujuan Zhai Jia Zhao |
author_sort | Yan Ding |
collection | DOAJ |
description | Predicting impending failure of hard disk drives (HDDs) is crucial to avoid losing essential data and service downtime. However, most HDD failure prediction is being challenged by using labelled data itself to evaluate failure rate, while the fact that HDDs deteriorate gradually cannot be described and exploited suitably. Most works on the Self-Monitoring and Reporting Technology (SMART) system attributes utilize simple and traditional methods from machine learning and statistics to achieve HDD failure prediction. So, we propose a novel two-level prediction model Dab, hard Drive failure prediction based on deep Auto-coder and Big data learning, to exploit SMART data for better online HDD failure prediction, constructing detection sub-models of anomaly and health degree. With better accuracy, better performance, better prediction earnings, and proactive fault tolerance, Dab has reduced false alarm rate (FAR) and maintenance cost, and improved failure detection rate (FDR), reliability and robustness of large-scale storage systems. |
first_indexed | 2024-03-12T00:23:50Z |
format | Article |
id | doaj.art-258f1f37acaa484c928a1f80abd30204 |
institution | Directory Open Access Journal |
issn | 0954-0091 1360-0494 |
language | English |
last_indexed | 2024-03-12T00:23:50Z |
publishDate | 2022-12-01 |
publisher | Taylor & Francis Group |
record_format | Article |
series | Connection Science |
spelling | doaj.art-258f1f37acaa484c928a1f80abd302042023-09-15T10:47:59ZengTaylor & Francis GroupConnection Science0954-00911360-04942022-12-0134144947110.1080/09540091.2021.20083202008320Explore deep auto-coder and big data learning to hard drive failure prediction: a two-level semi-supervised modelYan Ding0Yunan Zhai1Yujuan Zhai2Jia Zhao3Changchun Institute of TechnologyJilin Communications PolytechnicChangchun University of TechnologyChangchun Institute of TechnologyPredicting impending failure of hard disk drives (HDDs) is crucial to avoid losing essential data and service downtime. However, most HDD failure prediction is being challenged by using labelled data itself to evaluate failure rate, while the fact that HDDs deteriorate gradually cannot be described and exploited suitably. Most works on the Self-Monitoring and Reporting Technology (SMART) system attributes utilize simple and traditional methods from machine learning and statistics to achieve HDD failure prediction. So, we propose a novel two-level prediction model Dab, hard Drive failure prediction based on deep Auto-coder and Big data learning, to exploit SMART data for better online HDD failure prediction, constructing detection sub-models of anomaly and health degree. With better accuracy, better performance, better prediction earnings, and proactive fault tolerance, Dab has reduced false alarm rate (FAR) and maintenance cost, and improved failure detection rate (FDR), reliability and robustness of large-scale storage systems.http://dx.doi.org/10.1080/09540091.2021.2008320drive failure predictiondeep auto-coder learninganomaly detectionhealth degree detectionbig data learning |
spellingShingle | Yan Ding Yunan Zhai Yujuan Zhai Jia Zhao Explore deep auto-coder and big data learning to hard drive failure prediction: a two-level semi-supervised model Connection Science drive failure prediction deep auto-coder learning anomaly detection health degree detection big data learning |
title | Explore deep auto-coder and big data learning to hard drive failure prediction: a two-level semi-supervised model |
title_full | Explore deep auto-coder and big data learning to hard drive failure prediction: a two-level semi-supervised model |
title_fullStr | Explore deep auto-coder and big data learning to hard drive failure prediction: a two-level semi-supervised model |
title_full_unstemmed | Explore deep auto-coder and big data learning to hard drive failure prediction: a two-level semi-supervised model |
title_short | Explore deep auto-coder and big data learning to hard drive failure prediction: a two-level semi-supervised model |
title_sort | explore deep auto coder and big data learning to hard drive failure prediction a two level semi supervised model |
topic | drive failure prediction deep auto-coder learning anomaly detection health degree detection big data learning |
url | http://dx.doi.org/10.1080/09540091.2021.2008320 |
work_keys_str_mv | AT yanding exploredeepautocoderandbigdatalearningtoharddrivefailurepredictionatwolevelsemisupervisedmodel AT yunanzhai exploredeepautocoderandbigdatalearningtoharddrivefailurepredictionatwolevelsemisupervisedmodel AT yujuanzhai exploredeepautocoderandbigdatalearningtoharddrivefailurepredictionatwolevelsemisupervisedmodel AT jiazhao exploredeepautocoderandbigdatalearningtoharddrivefailurepredictionatwolevelsemisupervisedmodel |