[1]ZHANG Mingquan,WANG Baoxing.Disk failure prediction in data centers based on ECA-TCN[J].CAAI Transactions on Intelligent Systems,2025,20(2):389-399.[doi:10.11992/tis.202310043]
Copy

Disk failure prediction in data centers based on ECA-TCN

CAAI Transactions on Intelligent Systems[ISSN 1673-4785/CN 23-1538/TP] Volume: 20 Number of periods: 2025 2 Page number: 389-399 Column: 学术论文—机器感知与模式识别 Public date: 2025-03-05
Title:
Disk failure prediction in data centers based on ECA-TCN
Author(s):
ZHANG Mingquan1; 2;  WANG Baoxing1; 2
1. School of Control and Computer Engineering, North China Electric Power University, Baoding 071003, China;
2. Engineering Research Center of Intelligent Computing for Complex Energy Systems Ministry of Education, North China Electric Power University
Keywords:
disk failure prediction; long short-term memory network; recurrent neural network; dilated convolution; efficient channel attention mechanism; neural network model; time series prediction; deep learning optimization
CLC:
TP391.4
DOI:
10.11992/tis.202310043
Abstract:
With the continuous expansion of the scale of the data center, disk failure has an increasing impact on the stability of the data center. Current prediction methods still have shortcomings in the face of large-scale, high-dimensional and long sequence of disk running data. This paper proposes an efficient channel attention-temporal convolutional network (ECA-TCN) model. By combining the advantages of one-dimensional convolution of traditional convolutional neural network, integrating dilated convolution and residual structure, and introducing attention mechanism, the model can improve the accuracy and stability of disk failure prediction. In the experiment, the ECA-TCN model is compared with other classical deep learning methods. The experimental results show that the ECA-TCN model has high accuracy and stability in the disk failure prediction task.
References:
[1] RINCóN C C A, P?RIS J F, VILALTA R, et al. Disk failure prediction in heterogeneous environments[C]//2017 International Symposium on Performance Evaluation of Computer and Telecommunication Systems. Seattle: IEEE, 2017: 1-7.
[2] CHAVES I C, DE PAULA M R P, LEITE L G M, et al. BaNHFaP: a Bayesian network based failure prediction approach for hard disk drives[C]//2016 5th Brazilian Conference on Intelligent Systems. Recife: IEEE, 2016: 427-432.
[3] HAMERLY G, ELKAN C. Bayesian approaches to failure prediction for disk drives[C]//Proceedings of the Eighteenth International Conference on Machine Learning. San Francisco: Morgan Kaufmann Publishers Inc., 2001: 202-209.
[4] ZHANG Mingyu, GE Wenqiang, TANG Ruichun, et al. Hard disk failure prediction based on blending ensemble learning[J]. Applied sciences, 2023, 13(5): 3288.
[5] FULP E W, FINK G A, HAACK J. Predicting computer system failures using support vector machines[C]//Proceedings of the First USENIX conference on Analysis of system logs. USA: USENIX Association, 2008: 5.
[6] LI Jing, JI Xinpu, JIA Yuhan, et al. Hard drive failure prediction using classification and regression trees[C]//2014 44th Annual IEEE/IFIP International Conference on Dependable Systems and Networks. Atlanta: IEEE, 2014: 383-394.
[7] LI Jing, STONES R J, WANG Gang, et al. Hard drive failure prediction using decision trees[J]. Reliability engineering & system safety, 2017, 164: 55-65.
[8] SHEN Jing, WAN Jian, LIM S J, et al. Random-forest-based failure prediction for hard disk drives[J]. International journal of distributed sensor networks, 2018, 14(11): 155014771880648.
[9] 李国, 常甜甜, 李静. 基于变权重随机森林的硬盘故障预测方法[J]. 计算机工程与设计, 2021, 42(10): 2988-2994.
LI Guo, CHANG Tiantian, LI Jing. Hard disk failure prediction method based on variable weight random forest[J]. Computer engineering and design, 2021, 42(10): 2988-2994.
[10] 乔旭坤, 李顺, 李君, 等. 基于机器学习的硬盘故障预测研究[J]. 计算机技术与发展, 2022, 32(6): 215-220.
QIAO Xukun, LI Shun, LI Jun, et al. Research on hard disk failure prediction based on machine learning[J]. Computer technology and development, 2022, 32(6): 215-220.
[11] 李新鹏, 高欣, 何杨, 等. 不平衡数据集下基于自适应加权Bagging-GBDT算法的磁盘故障预测模型[J]. 微电子学与计算机, 2020, 37(3): 14-19.
LI Xinpeng, GAO Xin, HE Yang, et al. Prediction model of disk failure based on adaptive weighted Bagging-GBDT algorithm under imbalanced dataset[J]. Microelectronics & computer, 2020, 37(3): 14-19.
[12] SHI Junjie, DU Jing, REN Yingwen, et al. Convolution-LSTM-based mechanical hard disk failure prediction by sensoring S. M. A. R. T. indicators[J]. Journal of sensors, 2022(5): 7832117.
[13] SHEN Jing, REN Yongjian, WAN Jian, et al. Hard disk drive failure prediction for mobile edge computing based on an LSTM recurrent neural network[J]. Mobile information systems, 2021(2): 8878364.
[14] YANG Hongzhang, LI Zongzhao, QIANG Huiyuan, et al. ZTE-predictor: disk failure prediction system based on LSTM[C]//2020 50th Annual IEEE-IFIP International Conference on Dependable Systems and Networks-Supplemental Volume. Valencia: IEEE, 2020: 17-20.
[15] 兰云龙. 基于深度学习的磁盘健康度评估与故障预测技术研究[D]. 杭州: 杭州电子科技大学, 2017.
LAN Yunlong. Research on disk health evaluation and fault prediction technology based on deep learning[D]. Hangzhou: Hangzhou Dianzi University, 2017.
[16] 姜少彬, 杜春, 陈浩, 等. 一种硬盘故障预测的非监督对抗学习方法[J]. 西安电子科技大学学报, 2020, 47(2): 118-125.
JIANG Shaobin, DU Chun, CHEN Hao, et al. Unsupervised adversarial learning method for hard disk failure prediction[J]. Journal of Xidian University, 2020, 47(2): 118-125.
[17] HU Lihan, HAN Lixin, XU Zhenyuan, et al. A disk failure prediction method based on LSTM network due to its individual specificity[J]. Procedia computer science, 2020, 176: 791-799.
[18] WU Jian, YU Haiyang, YANG Zhen, et al. Disk failure prediction with multiple channel convolutional neural network[C]//2021 International Joint Conference on Neural Networks. Shenzhen: IEEE, 2021: 1-8.
[19] XU Chang, WANG Gang, LIU Xiaoguang, et al. Health status assessment and failure prediction for hard drives with recurrent neural networks[J]. IEEE transactions on computers, 2016, 65(11): 3502-3508.
[20] HAI Qinda, ZHANG Shuangwang, LIU Chang, et al. Hard disk drive failure prediction based on GRU neural network[C]//2022 IEEE/CIC International Conference on Communications in China. Sanshui: IEEE, 2022: 696-701.
[21] XU Shicheng, XU Xiaolong. ConvTrans-TPS: a convolutional transformer model for disk failure prediction in large-scale network storage systems[C]//2023 26th International Conference on Computer Supported Cooperative Work in Design. Rio de Janeiro: IEEE, 2023: 1318-1323.
[22] SUN Xiaoyi, CHAKRABARTY K, HUANG Ruirui, et al. System-level hardware failure prediction using deep learning[C]//2019 56th ACM/IEEE Design Automation Conference. Las Vegas: IEEE, 2019: 1-6.
[23] GUAN Yunchuan, LIU Yu, ZHOU Ke, et al. A disk failure prediction model for multiple issues[J]. Frontiers of information technology & electronic engineering, 2023, 24(7): 964-980.
[24] XIAO Jiang, XIONG Zhuang, WU Song, et al. Disk failure prediction in data centers via online learning[C]//Proceedings of the 47th International Conference on Parallel Processing. Eugene: ACM, 2018: 1-10.
[25] ZHANG Ji, ZHOU Ke, HUANG Ping, et al. Transfer learning based failure prediction for minority disks in large data centers of heterogeneous disk systems[C]//Proceedings of the 48th International Conference on Parallel Processing. Kyoto: ACM, 2019: 1-10.
[26] HAN Shujie, LEE P P C, SHEN Zhirong, et al. StreamDFP: a general stream mining framework for adaptive disk failure prediction[J]. IEEE transactions on computers, 2023, 72(2): 520-534.
[27] 关东海, 赵瑞, 袁伟伟, 等. 一种基于迁移学习和主动学习的硬盘故障预测方法及系统[P]. 中国: CN111949459A, 2020.
Guan Donghai, ZHAO Rui, YUAN Weiwei, et al. A hard disk failure prediction method and system based on transfer learning and active learning[P]. China: CN111949459A, 2020.
[28] LU Sidi, LUO Bing, Patel T, et al. Making disk failure predictions SMARTer![C]//Proceedings of the 18th USENIX Conference on File and Storage Technologies. Santa Clara: USENIX Association, 2020: 151-167.
[29] HAN Shujie, LEE P, XU Fan, et al. An in-depth study of correlated failures in production SSD-based data centers[C]//19th USENIX Conference on File and Storage Technologies. Olivia: USENIX Association, 2021: 417-429.
[30] WANG Wang, TANG Xuehai, ZHOU Biyu, et al. Improving disk failure detection accuracy via data augmentation[C]//2022 IEEE/ACM 30th International Symposium on Quality of Service. Oslo: IEEE, 2022: 1-10.
[31] WANG Qilong, WU Banggu, ZHU Pengfei, et al. ECA-net: efficient channel attention for deep convolutional neural networks[C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle: IEEE, 2020: 11531-11539.
[32] 李倩玉, 王蓓, 金晶, 等. 基于双向LSTM卷积网络与注意力机制的自动睡眠分期模型[J]. 智能系统学报, 2022, 17(3): 523-530.
LI Qianyu, WANG Bei, JIN Jing, et al. Automatic sleep staging model based on the bi-directional LSTM convolutional network and attention mechanism[J]. CAAI transactions on intelligent systems, 2022, 17(3): 523-530.
Similar References:

Memo

-

Last Update: 2025-03-05

Copyright © CAAI Transactions on Intelligent Systems