A summary of approaches to identify hard disk failure through the utilization of machine learning algorithms

Askarpour, Somayeh; Saberi Anari, Maryam

doi:10.22075/ijnaa.2023.31039.4551

A summary of approaches to identify hard disk failure through the utilization of machine learning algorithms

Document Type : Review articles

Authors

Somayeh Askarpour

Maryam Saberi Anari

Department of Computer Engineering, Technical and Vocational University (TVU),Tehran, Iran

10.22075/ijnaa.2023.31039.4551

Abstract

This article delves into the techniques employed for identifying failures in hard disks through the utilization of machine learning algorithms. Hard disks serve as essential components within computer systems, and as they age and undergo repetitive usage, they may manifest indications of failure or inadequate performance, culminating in data loss and system malfunction. Consequently, the early detection and anticipation of hard disk failures are of utmost significance. Recent advancements in machine learning methods have enabled the precise detection of hard disk failures within a short timeframe. Within this investigation, we explore the foundational concepts pertaining to hard disks and their failures. We scrutinize various machine learning algorithms employed for the detection of hard disk failures. Furthermore, we introduce performance evaluation metrics for failure detection models. The challenges and limitations in the detection of hard disk failures are discussed, along with potential strategies for enhancing system performance and accuracy.

Keywords

Hard drives

failures

identification

machine learning

deep neural networks

[1] M. Fadavi Amiri, M. Hosseinzadeh, and S.M.R. Hashemi, Improving image segmentation using artificial neural networks and evolutionary algorithms, Int. J. Nonlinear Anal. Appl. Article in Press, doi: 10.22075/IJNAA. 2023.30232.4371

[2] A. Ghanbari Sorkhi, M. Iranpour Mobarakeh, S.M.R. Hashemi, and M Faridpour, Predicting drug-target interaction based on bilateral local models using a decision tree-based hybrid support vector machine, Int. J. Nonlinear Anal. Appl. 12 (2021), no. 2, 135–144.

[3] G. Hamerly and C. Elkan, Bayesian approaches to failure prediction for disk drives, ICML. 1 (2001), 202–209.

[4] G.F. Hughes, J.F. Murray, K. Kreutz-Delgado, and C. Elkan, Improved disk-drive failure warnings, IEEE Trans. Reliab. 51 (2002), no. 3, 350–357.

[5] J.F. Murray, G.F. Hughes and K. Kreutz-Delgado, Machine learning methods for predicting failures in hard drives: A multiple-instance application, J. Mach. Learn. Res. 6 (2005), 783–816.

[6] J. Shen, J. Wan, S.J. Lim, and L. Yu, Random-forest-based failure prediction for hard disk drives, Int. J. Distrib. Sensor Netw. 14 (2018), no. 11.

[7] Y. Wang, Q. Miao, E.W. Ma, K.L. Tsui and M.G. Pecht, Online anomaly detection for hard disk drives based on Mahalanobis distance, IEEE Trans. Reliab. 62 (2013), no. 1, 136–145.

[8] Y. Wang, E.W. Ma, T.W. Chow, and K.L. Tsui, A two-step parametric method for failure prediction in hard disk drives, IEEE Trans. Industr. Inf. 10 (2013), no. 1, 419–430.

[9] J. Xiao, Z. Xiong, S. Wu, Y. Yi, H. Jin and K. Hu, Disk failure prediction in data centers via online learning, Proc. 47th Int. Conf. Parallel Process., 2018, pp. 1–10.

[10] C. Xu, G. Wang, X. Liu, D. Guo, and T.Y. Liu, Health status assessment and failure prediction for hard drives with recurrent neural networks, IEEE Trans. Comput. 65 (2016), no. 11, 3502–3508.