BaNHFaP: A Bayesian Network Based Failure Prediction Approach for Hard Disk Drives

Chaves, Iago C.; Paula, Manoel Rui P.; Leite, Lucas G. M.; Queiroz, Lucas P.; Gomes, João P. P.; Machado, Javam C.

doi:10.1109/bracis.2016.083

Cited by 24 publications

(8 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…indicators in a timely and accurate manner. In recent years, several researchers have proposed methods for mechanical hard disk failure prediction, mainly divided into mathematicsbased methods [2,3] and machine learning-based failure prediction method [4]. These methods do not adequately consider the problems of removing unnecessary S.M.A.R.T.…”

Section: Introductionmentioning

confidence: 99%

Convolution-LSTM-Based Mechanical Hard Disk Failure Prediction by Sensoring S.M.A.R.T. Indicators

Shi

Ren

et al. 2022

Journal of Sensors

View full text Add to dashboard Cite

The traditional Infrastructure as a Service (IaaS) cloud platform tends to realize high data availability by introducing dedicated storage devices. However, this heterogeneous architecture has high maintenance cost and might reduce the performance of virtual machines. In homogeneous IaaS cloud platform, servers in the platform would uniformly provide computing resources and storage resources, which effectively solve the above problems, although corresponding mechanisms need to be introduced to improve data availability. Efficient storage resource availability management is one of the key methods to improve data availability. As mechanical hard disk is the main way to realize data storage in IaaS cloud platform at present, timely and accurate prediction of mechanical hard disk failure and active data backup and migration before mechanical hard disk failure would effectively improve the data availability of IaaS cloud platform. In this paper, we propose an improved algorithm for early warning of mechanical hard disk failures. We first use the Relief feature selection algorithm to perform parameter selection. Then, we use the zero-sum game idea of Generative Adversarial Networks (GAN) to generate fewer category samples to achieve a balance of sample data. Finally, an improved Long Short-Term Memory (LSTM) model called Convolution-LSTM (C-LSTM) is used to complete accurate detection of hard disk failures and achieve fault warning. We evaluate several models using precision, recall, and Area Under Curve (AUC) value, and extensive experiments show that our proposed algorithm outperforms other algorithms for mechanical hard disk warning.

show abstract

Section: Introductionmentioning

confidence: 99%

Convolution-LSTM-Based Mechanical Hard Disk Failure Prediction by Sensoring S.M.A.R.T. Indicators

Shi

Ren

et al. 2022

Journal of Sensors

View full text Add to dashboard Cite

show abstract

“…As a result, the authors were forced to discard parameters that were absent in at least 90% of the disks, after which 21 parameters remained. In [10][11][12][13][14], SMART parameters of the specified data set were used to determine the intensity and prediction of disk drive failures. Therefore, the question on assessment of the information storage device reliability based on SMART parameter values is really important for ensuring data security in any organization.…”

Section: Resultsmentioning

confidence: 99%

Dependence of Reallocated Sectors Count on HDD Power-on Time

Nasyrov¹,

Nasyrov²,

Nasyrov³

et al. 2018

IJET

View full text Add to dashboard Cite

The problem of SMART-data ambiguity in different models of hard disk drives of the same manufacturers is considered. This circumstance creates obstacles for the use of SMART technology when assessing and predicting the reliability of storage devices. The scientific task of the work is to study the dependence of the hard disk failure probability on the reliability parameters values for each individual storage device of any model of any manufacturer. In the course of the study, two interrelated parameters were analyzed: “5 Reallocated sectors count” and “9 Power-on hours” (the number of hours spent in the on state). As a result of the analysis, two types of dependences were revealed: drooping and dome shaped. The first means the maximum failure frequency of information storage devices immediately after commissioning, the second - after a certain period of time, actually coinciding with the warranty period for the products (two years). With the help of clustering in plane according to the coordinates of the number of reallocated sectors and the time of operation, two different reasons for the failure of the drives were discovered: due to deterioration of the disk surface and due to errors in the positioning of the read / write heads. Based on the variety of types of causes and consequences of equipment failure, the task of individual assessment of an individual data storage device reliability is proposed to be solved using several parameters simultaneously.

show abstract

“…As a result, the authors were forced to discard parameters that were absent in at least 90% of the disks, after which 21 parameters remained. In [11][12][13][14][15], SMART parameters of the specified data set were also used to determine the intensity and prediction of disk drive failures. Therefore, the choice of parameters for assessing the reliability of information storage devices based on the values of SMART parameters is really important for ensuring data security in any organization.…”

Section: Discussionmentioning

confidence: 99%

Data Mining for Information Storage Reliability Assessment by Relative Values

Nasyrov¹,

Nasyrov²,

Nasyrov³

et al. 2018

IJET

View full text Add to dashboard Cite

The data ambiguity problem for heterogeneous sets of equipment reliability indicators is considered. In fact, the same manufacturers do not always unambiguously fill the SMART parameters with the corresponding values for their different models of hard disk drives. In addition, some of the parameters are sometimes empty, while the other parameters have only zero values.The scientific task of the research consists in the need to define such a set of parameters that will allow us to obtain a comparative assessment of the reliability of each individual storage device of any model of any manufacturer for its timely replacement.The following conditions were used to select the parameters suitable for evaluating their relative values:1) The parameter values for normally operating drives should always be greater or lower than for the failed ones;2) The monotonicity of changes in the values of parameters in the series should be observed: normally working, withdrawn prematurely, failed;3) The first two conditions must be fulfilled both in general and in particular, for example, for the drives of each brand separately.Separate averaging of the values for normally operating, early decommissioned and failed storage media was performed. The maximum of these three values was taken as 100%. The relative distribution of values for each parameter was studied.Five parameters were selected (5 – “Reallocated sectors count”, 7 – “Seek error rate”, 184 – “End-to-end error”, 196 – “Reallocation event count”, 197 – “Current pending sector count”, plus another four (1 – “Raw read error rate”, 10 – “Spin-up retry counts”, 187 – “Reported uncorrectable errors”, 198 – “Uncorrectable sector counts”), which require more careful analysis, and one (194 – “Hard disk assembly temperature”) for prospective use in solid-state drives, as a result of the relative value study of their suitability for use upon evaluating the reliability of data storage devices.

show abstract

BaNHFaP: A Bayesian Network Based Failure Prediction Approach for Hard Disk Drives

Cited by 24 publications

References 14 publications

Convolution-LSTM-Based Mechanical Hard Disk Failure Prediction by Sensoring S.M.A.R.T. Indicators

Convolution-LSTM-Based Mechanical Hard Disk Failure Prediction by Sensoring S.M.A.R.T. Indicators

Dependence of Reallocated Sectors Count on HDD Power-on Time

Data Mining for Information Storage Reliability Assessment by Relative Values

Contact Info

Product

Resources

About