一个针对多种问题的磁盘故障预测模型

关云川; 刘渝; 周可; 李强; 王团结; 李辉

doi:10.1631/FITEE.2200488

Your Location：

Home >

Browse articles >

一个针对多种问题的磁盘故障预测模型

常规文章 | Updated：2023-07-24

- 一个针对多种问题的磁盘故障预测模型
  Enhanced Publication
- A disk failure prediction model for multiple issues
- 信息与电子工程前沿（英文） 2023年24卷第7期页码：964-979
- Affiliations：
  
  1.Wuhan National Laboratory for Optoelectronics, Huazhong University of Science and Technology, Wuhan 430074, China
  2.School of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan 430074, China
  3.Inspur Electronic Informantion Industry Co., Ltd., Beijing 250000, China
- Author bio：
  
  †E-mail: hustgyc@hust.edu.cn
  ‡Corresponding author
- Funds：
  
  National Natural Science Foundation of China(61902135);Shandong Provincial Natural Science Foundation, China(ZR2019LZH003)
- DOI：10.1631/FITEE.2200488
  中图分类号： TN333
- 纸质出版日期：2023-07-0 ，
  
  收稿日期：2022-10-19，
  
  录用日期：2023-06-13
- Accepted：
Scan QR Code
关云川, 刘渝, 周可, 等. 一个针对多种问题的磁盘故障预测模型[J]. 信息与电子工程前沿（英文）, 2023,24(7):964-979.

YUNCHUAN GUAN, YU LIU, KE ZHOU, et al. A disk failure prediction model for multiple issues. [J]. Frontiers of information technology & electronic engineering, 2023, 24(7): 964-979.
关云川, 刘渝, 周可, 等. 一个针对多种问题的磁盘故障预测模型[J]. 信息与电子工程前沿（英文）, 2023,24(7):964-979. DOI： 10.1631/FITEE.2200488.

YUNCHUAN GUAN, YU LIU, KE ZHOU, et al. A disk failure prediction model for multiple issues. [J]. Frontiers of information technology & electronic engineering, 2023, 24(7): 964-979. DOI： 10.1631/FITEE.2200488.

摘要

磁盘故障预测方法在单一问题上的解决方案十分成熟，例如磁盘异构问题、模型老化问题和小样本问题。然而，由于这些问题经常同时存在，只能处理其中一个问题的模型在实际预测中存在偏差。目前针对不同问题的解决方案经常相互冲突，然而现有磁盘故障预测方法通常简单地融合各种模型，缺乏在面对多个问题时对训练数据准备和学习模式的讨论。为此，提出一种多属性数据划分方法（MDP），来探索针对多个问题的训练数据准备。引入与模型无关的元学习算法（MAML），对被划分的多个数据子集进行多任务学习。基于这些改进，提出一种名为MDP-MAML的磁盘故障预测模型。MDP解决了数据不均匀划分和按时间划分的挑战，而MAML解决了针对多个问题小样本学习的问题。此外，MDP-MAML能够适应新出现的问题并进行学习和预测。在两个实际数据中心的数据集上，与最先进方法相比，MDP-MAML将曲线下面积（AUC）从0.85提升至0.89，将误检率（FDR）从0.85提升至0.91，将误报率（FAR）从4.88%降低至2.85%。

Abstract

Disk failure prediction methods have been useful in handing a single issue

e.g.

heterogeneous disks

model aging

and minority samples. However

because these issues often exist simultaneously

prediction models that can handle only one will result in prediction bias in reality. Existing disk failure prediction methods simply fuse various models

lacking discussion of training data preparation and learning patterns when facing multiple issues

although the solutions to different issues often conflict with each other. As a result

we first explore the training data preparation for multiple issues via a data partitioning pattern

i.e.

our proposed multi-property data partitioning (MDP). Then

we consider learning with the partitioned data for multiple issues as learning multiple tasks

and introduce the model-agnostic meta-learning (MAML) framework to achieve the learning. Based on these improvements

we propose a novel disk failure prediction model named MDP-MAML. MDP addresses the challenges of uneven partitioning and difficulty in partitioning by time

and MAML addresses the challenge of learning with multiple domains and minor samples for multiple issues. In addition

MDP-MAML can assimilate emerging issues for learning and prediction. On the datasets reported by two real-world data centers

compared to state-of-the-art methods

MDP-MAML can improve the area under the curve (AUC) and false detection rate (FDR) from 0.85 to 0.89 and from 0.85 to 0.91

respectively

while reducing the false alarm rate (FAR) from 4.88% to 2.85%.

关键词

存储系统可靠性磁盘故障预测自我监测、分析及报告技术（SMART）机器学习

Keywords

Storage system reliabilityDisk failure predictionSelf-monitoring analysis and reporting technology (SMART)Machine learning

references

Backblaze , 2018. The Backblaze Hard Drive Data and Stats. https://www.backblaze.com/b2/hard-drive-test-data.htmlhttps://www.backblaze.com/b2/hard-drive-test-data.html [Accessed on Oct. 18, 2022].

Botezatu MM, Giurgiu I, Bogojeska J, et al., 2016. Predicting disk replacement towards reliable data centers. Proc 22nd ACM SIGKDD Int Conf on Knowledge Discovery and Data Mining, p.39-48. doi: 10.1145/2939672.2939699http://doi.org/10.1145/2939672.2939699

Buffelli D, Vandin F, 2022. Graph representation learning for multi-task settings: a meta-learning approach. Int Joint Conf on Neural Networks, p.1-8. doi: 10.1109/IJCNN55064.2022.9892010http://doi.org/10.1109/IJCNN55064.2022.9892010

Finn C, Abbeel P, Levine S, 2017. Model-agnostic meta-learning for fast adaptation of deep networks. Proc 34th Int Conf on Machine Learning, p.1126-1135.

Frikha A, Krompaß D, Köpken HG, et al., 2021. Few-shot one-class classification via meta-learning. Proc AAAI Conf on Artificial Intelligence, p.7448-7456. doi: 10.1609/aaai.v35i8.16913http://doi.org/10.1609/aaai.v35i8.16913

Han SJ, Lee PPC, Xu F, et al., 2021. An in-depth study of correlated failures in production SSD-based data centers. Proc 19th USENIX Conf on File and Storage Technologies, p.417-429.

He HB, Garcia EA, 2009. Learning from imbalanced data. IEEE Trans Knowl Data Eng, 21(9):1263-1284. doi: 10.1109/TKDE.2008.239http://doi.org/10.1109/TKDE.2008.239

Hospedales T, Antoniou A, Micaelli P, et al., 2022. Meta-learning in neural networks: a survey. IEEE Trans Patt Anal Mach Intell, 44(9):5149-5169. doi: 10.1109/TPAMI.2021.3079209http://doi.org/10.1109/TPAMI.2021.3079209

Jiang TM, Zeng JF, Zhou K, et al., 2019. Lifelong disk failure prediction via GAN-based anomaly detection. IEEE 37th Int Conf on Computer Design, p.199-207. doi: 10.1109/ICCD46524.2019.00033http://doi.org/10.1109/ICCD46524.2019.00033

Lake BM, Salakhutdinov R, Gross J, et al., 2011. One shot learning of simple visual concepts. Proc 33rd Annual Meeting of the Cognitive Science Society, p.2568-2573.

Ling CX, Huang J, Zhang H, et al., 2003. AUC: a statistically consistent and more discriminating measure than accuracy. Proc 18th Int Joint Conf on Artificial Intelligence, p.519-524.

Lu SD, Luo B, Patel T, et al., 2020. Making disk failure predictions smarter! Proc 18th USENIX Conf on File and Storage Technologies, p.151-167.

Luo C, Zhao P, Qiao B, et al., 2021. NTAM: neighborhood-temporal attention model for disk failure prediction in cloud platforms. Proc Web Conf, p.1181-1191. doi: 10.1145/3442381.3449867http://doi.org/10.1145/3442381.3449867

Mao YR, Wang ZK, Liu WW, et al., 2022. MetaWeighting: learning to weight tasks in multi-task learning. Findings of the Association for Computational Linguistics: ACL 2022, p.3436-3448. doi: 10.18653/v1/2022.findings-acl.271http://doi.org/10.18653/v1/2022.findings-acl.271

Nichol A, Achiam J, Schulman J, 2018. On first-order meta-learning algorithms. https://arxiv.org/abs/1803.02999https://arxiv.org/abs/1803.02999

Pereira FLF, dos Santos Lima FD, de Moura Leite LG, et al., 2017. Transfer learning for Bayesian networks with application on hard disk drives failure prediction. Brazilian Conf on Intelligent Systems, p.228-233. doi: 10.1109/BRACIS.2017.64http://doi.org/10.1109/BRACIS.2017.64

Pinheiro E, Weber WD, Barroso LA, 2007. Failure trends in a large disk drive population. Proc 5th USENIX Conf on File and Storage Technologies, p.17-28.

Rincón CA, Pâris JF, Vilalta R, et al., 2017. Disk failure prediction in heterogeneous environments. Int Symp on Performance Evaluation of Computer and Telecommunication Systems, p.1-7. doi: 10.23919/SPECTS.2017.8046776http://doi.org/10.23919/SPECTS.2017.8046776

Shen J, Ren YJ, Wan J, et al., 2021. Hard disk drive failure prediction for mobile edge computing based on an LSTM recurrent neural network. Mob Inform Syst, 2021:1-12. doi: 10.1155/2021/8878364http://doi.org/10.1155/2021/8878364

Sun XY, Chakrabarty K, Huang RR, et al., 2019. System-level hardware failure prediction using deep learning. Proc 56th ACM/IEEE Design Automation Conf, p.1-6. doi: 10.1145/3316781.3317918http://doi.org/10.1145/3316781.3317918

Vaswani A, Shazeer N, Parmar N, et al., 2017. Attention is all you need. Proc 31st Int Conf on Neural Information Processing Systems, p.6000-6010.

Wang JD, Lan CL, Liu C, et al., 2021. Generalizing to unseen domains: a survey on domain generalization. Proc 30th Int Joint Conf on Artificial Intelligence, p.4627-4635. doi: 10.24963/ijcai.2021/628http://doi.org/10.24963/ijcai.2021/628

Xiao J, Xiong Z, Wu S, et al., 2018. Disk failure prediction in data centers via online learning. Proc 47th Int Conf on Parallel Processing, p.1-10. doi: 10.1145/3225058.3225106http://doi.org/10.1145/3225058.3225106

Xie YW, Feng D, Wang F, et al., 2018. OME: an optimized modeling engine for disk failure prediction in heterogeneous datacenter. IEEE 36th Int Conf on Computer Design, p.561-564. doi: 10.1109/ICCD.2018.00089http://doi.org/10.1109/ICCD.2018.00089

Zhang J, Huang P, Zhou K, et al., 2020a. HDDse: enabling high-dimensional disk state embedding for generic failure detection system of heterogeneous disks in large data centers. Proc USENIX Annual Technical Conf, p.111-126.

Zhang J, Zhou K, Huang P, et al., 2020b. Minority disk failure prediction based on transfer learning in large data centers of heterogeneous disk systems. IEEE Trans Parall Distrib Syst, 31(9):2155-2169. doi: 10.1109/TPDS.2020.2985346http://doi.org/10.1109/TPDS.2020.2985346

Zhang YQ, Hao WW, Niu B, et al., 2023. Multi-view feature-based SSD failure prediction: what, when, and why. Proc 21st USENIX Conf on File and Storage Technologies, p.409-424.

Zhou Y, Wang F, Feng D, 2022. A disk failure prediction method based on active semi-supervised learning. ACM Trans Stor, 18(4):1-33. doi: 10.1145/3523699http://doi.org/10.1145/3523699

Zhu BP, Wang G, Liu XG, et al., 2013. Proactive drive failure prediction for large scale storage systems. IEEE 29th Symp on Mass Storage Systems and Technologies, p.1-5. doi: 10.1109/MSST.2013.6558427http://doi.org/10.1109/MSST.2013.6558427

浏览量

142

Downloads

CSCD

文章被引用时，请邮件提醒。

Submit

工具集

关联资源

Domain adaptation in reinforcement learning: a comprehensive and systematic study

Towards sustainable adversarial training with successive perturbation generation

Advances and challenges in artificial intelligence text generation

Data-driven soft sensors in blast furnace ironmaking: a survey

Machine learning based altitude-dependent empirical LoS probability model for air-to-ground communications