Fault-tolerant method for industrial IoT edge computing based on sparse graph attention

doi:10.11772/j.issn.1001-9081.2025091151

Journal of Computer Applications ›› 2026, Vol. 46 ›› Issue (10): 3242-3249.DOI: 10.11772/j.issn.1001-9081.2025091151

• Cyber security • Previous Articles

Fault-tolerant method for industrial IoT edge computing based on sparse graph attention

Yuqing NIU¹^,²^,³^,⁴, Zhiyong ZHANG¹^,²^,³^,⁴(), Zhongya ZHANG¹^,²^,³^,⁴, Hang ZHANG¹^,²^,³^,⁴

^1.School of Information Engineering （School of Artificial Intelligence），Henan University of Science and Technology，Luoyang Henan 471023，China
^2.Henan International Joint Laboratory of Cyberspace Security Applications （Henan University of Science and Technology），Luoyang Henan 471023，China
^3.Henan Intelligent Manufacturing Big Data Development Innovation Laboratory （Henan University of Science and Technology），Luoyang Henan 471023，China
^4.Institute of Artificial Intelligence Innovations，Henan University of Science and Technology，Luoyang Henan 471023，China

Received:2025-09-29 Revised:2025-10-29 Accepted:2025-10-30 Online:2025-11-05 Published:2026-10-10
Contact: Zhiyong ZHANG
About author:NIU Yuqing， born in 2001， M. S. candidate. Her research interests include industrial internet of things， edge computing.
ZHANG Zhongya， born in 1985， Ph. D.， lecturer. His research interests include quantum computing， symmetric cryptographic algorithms.
ZHANG Hang， born in 1991， Ph. D.， lecturer. His research interests include smart grid cybersecurity， artificial intelligence.
Supported by:
Key Research and Development Special Program of Henan Province(241111211400);Henan Province Science and Technology Research Project(242102211077);Henan Province University Key Scientific Research Project(23A520008);Henan Province Natural Science Foundation(252300421509)

基于稀疏图注意力的工业物联网边缘计算容错方法

牛钰清¹^,²^,³^,⁴, 张志勇¹^,²^,³^,⁴(), 张中亚¹^,²^,³^,⁴, 张航¹^,²^,³^,⁴

^1.河南科技大学信息工程学院（人工智能学院），河南洛阳 471023
^2.河南省网络空间安全应用国际联合实验室（河南科技大学），河南洛阳 471023
^3.河南省智能制造大数据发展创新实验室（河南科技大学），河南洛阳 471023
^4.河南科技大学人工智能创新研究院，河南洛阳 471023

通讯作者: 张志勇
作者简介:牛钰清（2001—），女，河南鹿邑人，硕士研究生，主要研究方向：工业物联网、边缘计算
张中亚（1985—），男，河南太康人，讲师，博士，主要研究方向：量子计算、对称密码算法
张航（1991—），男，河南南阳人，讲师，博士，主要研究方向：智能电网网络安全、人工智能。
基金资助:
河南省重点研发专项(241111211400);河南省科技攻关计划项目(242102211077);河南省高校重点科研项目(23A520008);河南省自然科学基金资助项目(252300421509)

Abstract

Abstract:

To address the issues of node overload and failure caused by resource constraints in Industrial Internet of Things （IIoT） edge computing environments， this paper proposed a fault-tolerant method based on edge intelligence — Sparse Graph ATtention-based Generative Adversarial Network （SGAT-GAN）. This method integrated a fault prediction mechanism and employed a Fault Embedding Encoder （FEE） to achieve real-time fault detection， classification， and prediction， thereby enhancing the system’s fault-tolerance capability. On this basis， this method combined Generative Adversarial Network （GAN） with a preemptive migration strategy to select the optimal strategy for intelligent fault recovery， thereby providing an efficient and intelligent solution for IIoT edge computing systems. Experimental results in a Raspberry Pi-based edge environment demonstrate that this method outperforms four state-of-the-art methods — Proactive Coordinated Fault Tolerance （PCFT）， Clustering-based Multiple Objective Dynamic Load Balancing technique （CMODLB）， self-supervised deep proxy-based edge computing fault tolerance method DeepFT， and Preemptive migration prediction Generative Adversarial Network （PreGAN） — in terms of average detection precision and average classification accuracy of faults. Specifically， compared with the best-performing state-of-the-art method PreGAN， the proposed method achieves improvements of 1.96 and 1.62 percentage points in these two metrics， respectively， validating its effectiveness and superiority in enhancing the reliability of IIoT edge computing systems.

Key words: Industrial Internet of Things (IIoT), edge computing, fault-tolerant method, fault prediction, Generative Adversarial Network (GAN)

摘要：

针对工业物联网（IIoT）边缘计算环境中因资源受限导致节点过载甚至故障的问题，提出一种基于边缘智能的容错方法——融合稀疏图注意力的生成对抗网络（SGAT-GAN）。该方法融合故障预测机制，通过故障嵌入编码器（FEE）技术实现故障的实时检测、分类与预测，提升系统的容错能力。在此基础上，结合生成对抗网络（GAN）和抢先迁移选择最优策略对故障进行智能补救，为IIoT边缘计算系统提供一种高效、智能的解决方案。在基于Raspberry Pi的边缘环境中的实验结果表明，该方法在故障平均检测精确率和平均分类准确率上优于主动协调容错（PCFT）、基于聚类的多目标动态负载均衡技术（CMODLB）、基于自监督深度代理模型的边缘计算容错方法（DeepFT）和预迁移预测网络（PreGAN）这4种先进方法。其中，相较于表现最佳的先进方法PreGAN，所提方法在这两项指标上分别提高了1.96和1.62个百分点，验证了该方法在提升IIoT边缘计算系统可靠性方面的有效性与优越性。

关键词: 工业物联网, 边缘计算, 容错方法, 故障预测, 生成对抗网络

CLC Number:

TP393.08

Yuqing NIU, Zhiyong ZHANG, Zhongya ZHANG, Hang ZHANG. Fault-tolerant method for industrial IoT edge computing based on sparse graph attention[J]. Journal of Computer Applications, 2026, 46(10): 3242-3249.

牛钰清, 张志勇, 张中亚, 张航. 基于稀疏图注意力的工业物联网边缘计算容错方法[J]. 《计算机应用》唯一官方网站, 2026, 46(10): 3242-3249.

Figures/Tables 12

Fig. 1 Overall system architecture

Fig. 2 Framework of SGAT-GAN method

Fig. 3 Sparse LSTM-based method （first time step）

Fig. 4 Loss curve of FEE training

Fig. 5 Loss curves of GAN training

Fig. 6 Heatmap of fault intervals predicted by SGAT-GAN method

Tab. 1 Comparison of fault detection results and standard deviations for different methods

方法	准确率	精确率	召回率	F1分数
PCFT	89.13±1.08	80.29±6.92	90.18±1.65	84.95±3.12
CMODLB	91.28±1.12	81.58±3.43	90.13±0.91	86.05±2.84
DeepFT	94.22±0.78	86.35±0.11	90.01±0.92	88.14±2.71
PreGAN	96.35±0.92	87.23±2.21	90.18±1.21	88.68±6.29
SGAT-GAN	91.74±1.47	89.19±1.87	98.82±0.20	93.63±1.06

Tab. 2 Comparison of classification accuracy and standard deviation for different methods

方法	准确率
DeepFT	82.27±2.58
PreGAN	91.63±2.48
SGAT-GAN	93.25±2.49

Fig. 7 Comparison of model energy consumption and transfer amount

Tab. 3 Comparison of experimental results for different temporal feature extraction methods

时间特征提取方法	准确率	F1分数
GRU	88.56±0.93	91.38±0.57
LSTM	91.33±2.32	93.37±1.65
稀疏LSTM	91.74±1.47	93.63±1.06

Tab. 4 Comparison of accuracy and F1 score for different spatial feature extraction methods

空间特征提取方法	准确率	F1分数
GCN	67.84±0.46	80.05±0.48
GIN	78.49±2.72	87.51±2.47
GAT	91.74±1.47	93.63±1.06

Fig. 8 Comparison of F1 score after quantization and pruning

References 31

[1]	Xu J， Tao H， Zhang X， et al. An adaptive multisignal framework for real-time fault diagnosis of rolling bearings［J］. IEEE Transactions on Instrumentation and Measurement， 2025， 74： No.3509816.
[2]	Tuli S， Ilager S， Ramamohanarao K， et al. Dynamic scheduling for stochastic edge-cloud computing environments using A3C learning and residual recurrent neural networks［J］. IEEE Transactions on Mobile Computing， 2022， 21（3）： 940-954.
[3]	Liu J， Xu H， Wang L， et al. Adaptive asynchronous federated learning in resource-constrained edge computing［J］. IEEE Transactions on Mobile Computing， 2023， 22（2）： 674-690.
[4]	Ristov S， Fahringer T， Peer D， et al. Resilient techniques against disruptions of volatile cloud resources［M］// Rak J， Hutchison D. Guide to disaster-resilient communication networks， CCN. Cham： Springer， 2020： 379-400.
[5]	Ataallah S M A， Nassar S M， Hemayed E E. Fault tolerance in cloud computing — survey［C］// ICENCO 2015. Piscataway： IEEE， 2015： 241-245.
[6]	Sivagami V M， Easwarakumar K S. An improved dynamic fault tolerant management algorithm during VM migration in cloud data center［J］. Future Generation Computer Systems， 2019， 98： 35-43.
[7]	Jia Y， Wang T， Qiu T， et al. Fault tolerance of stateful microservices for industrial edge scenarios［C］// JCC 2023. Piscataway： IEEE， 2023： 50-56.
[8]	Wang Y Y， Hsu C P， Huang C M， et al. Fault location prediction based on customer complaint amount［C］// APNOMS 2019. Piscataway： IEEE， 2019： 1-4.
[9]	Shayesteh B， Ebrahimzadeh A， Glitho R. Machine learning for predicting infrastructure faults and job failures in clouds： a survey［J］. IEEE Communications Magazine， 2025， 63（1）： 148-154.
[10]	Li J， Ding D， Tsung F. Directional PCA for fast detection and accurate diagnosis： a unified framework［J］. IEEE Transactions on Cybernetics， 2022， 52（11）： 11362-11372.
[11]	Jia Y， Ying L， Wang D， et al. Defect prediction of relay protection systems based on LSSVM-BNDT［J］. IEEE Transactions on Industrial Informatics， 2020， 17（1）： 710-719.
[12]	Yang Y， Mei J， Zhang Z， et al. Lightweight fault prediction method for edge networks［J］. IEEE Internet of Things Journal， 2024， 11（6）： 11117-11136.
[13]	Huang Q， Han Y， Zhang X， et al. FFKD-CGhostNet： a novel lightweight network for fault diagnosis in edge computing scenarios［J］. IEEE Transactions on Instrumentation and Measurement， 2023， 72： No.3536410.
[14]	Sharif A， Nickray M， Shahidinejad A. Fault-tolerant with load balancing scheduling in a fog-based IoT application［J］. IET Communications， 2020， 14（16）： 2646-2657.
[15]	Liu J， Wang S， Zhou A， et al. Using proactive fault-tolerance approach to enhance cloud service reliability［J］. IEEE Transactions on Cloud Computing， 2018， 6（4）： 1191-1202.
[16]	Negi S， Rauthan M M S， Vaisla K S， et al. CMODLB： an efficient load balancing approach in cloud computing environment［J］. The Journal of Supercomputing， 2021， 77（8）： 8787-8839.
[17]	An K， Lu J， Zhu Q， et al. Edge solution for real-time motor fault diagnosis based on efficient convolutional neural network［J］. IEEE Transactions on Instrumentation and Measurement， 2023， 72： No.3516912.
[18]	Xiao Y， Shao H， Lin J， et al. BCE-FL： a secure and privacy-preserving federated learning system for device fault diagnosis under non-IID condition in IIoT［J］. IEEE Internet of Things Journal， 2024， 11（8）： 14241-14252.
[19]	Tuli S， Casale G， Cherkasova L， et al. DeepFT： fault-tolerant edge computing using a self-supervised deep surrogate model［C］// IEEE INFOCOM 2023. Piscataway： IEEE， 2023： 1-10.
[20]	Tuli S， Casale G， Jennings N R. PreGAN： preemptive migration prediction network for proactive fault-tolerant edge computing［C］// IEEE INFOCOM 2022. Piscataway： IEEE， 2022： 670-679.
[21]	Chen Y， Yang Q， He S， et al. FTPipeHD： a fault-tolerant pipeline-parallel distributed training approach for heterogeneous edge devices［J］. IEEE Transactions on Mobile Computing， 2024， 23（4）： 3200-3212.
[22]	Al-Dulaimy A， Sicari C， Papadopoulos A V， et al. TOLERANCER： a fault tolerance approach for cloud manufacturing environments［C］// ETFA 2022. Piscataway： IEEE， 2022： 1-8.
[23]	Xie X， Wu X， Hu Q， et al. Multi-container migration strategy optimization for industrial robotics workflow based on hybrid tabu-evolutionary algorithm［J］. IEEE Transactions on Services Computing， 2024， 17（5）： 2640-2653.
[24]	Tuli S， Mahmud R， Tuli S， et al. FogBus： a blockchain-based lightweight framework for edge and fog computing［J］. Journal of Systems and Software， 2019， 154： 22-36.
[25]	Basu D， Wang X， Hong Y， et al. Learn-as-you-go with Megh： efficient live migration of virtual machines［J］. IEEE Transactions on Parallel and Distributed Systems， 2019， 30（8）： 1786-1801.
[26]	Tuli S， Casale G， Jennings N R. PreGAN+： semi-supervised fault prediction and preemptive migration in dynamic mobile edge environments［J］. IEEE Transactions on Mobile Computing， 2024， 23（6）： 6881-6895.
[27]	So R Q， Kent A R， Grill W M. Relative contributions of local cell and passing fiber activation and silencing to changes in thalamic fidelity during deep brain stimulation and lesioning： a computational modeling study［J］. Journal of Computational Neuroscience， 2012， 32（3）： 499-519.
[28]	Tuli S， Bansal R， Paul R， et al. TANGO： commonsense generalization in predicting tool interactions for mobile manipulators［C］// IJCAI 2021. California： IJCAI， 2021： 4197-4205.
[29]	Tuli S， Poojara S R， Srirama S N， et al. COSCO： container orchestration using co-simulation and gradient based optimization for fog computing environments［J］. IEEE Transactions on Parallel and Distributed Systems， 2022， 33（1）： 101-116.
[30]	Vaswani A， Shazeer N， Parmar N， et al. Attention is all you need［C］// NeurIPS 2017. Red Hook： Curran Associates Inc.， 2017： 6000-6010.
[31]	Tuli S， Gill S S， Xu M， et al. HUNTER： AI based holistic resource management for sustainable cloud computing［J］. Journal of Systems and Software， 2022， 184： No.111124.

Fault-tolerant method for industrial IoT edge computing based on sparse graph attention

基于稀疏图注意力的工业物联网边缘计算容错方法

RichHTML

PDF

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 12

References 31

Related Articles 15

Recommended Articles

Metrics

[1]	Chenyang WANG, Xiaoyu SHI, Jie GAN, Mingsheng SHANG. Trajectory-aware multi-agent cooperative task offloading method for vehicular edge computing [J]. Journal of Computer Applications, 2026, 46(9): 2910-2919.
[2]	Guanliang CHEN, Yi LIU, Yi YU. Heterogeneous multi-agent reinforcement learning enabled co-optimization of UAV 3D obstacle avoidance and edge computing [J]. Journal of Computer Applications, 2026, 46(9): 2898-2909.
[3]	Juan CHEN, Yujie CHEN, Zongling WU, Di TIAN, Jie ZHONG. User-centric satellite edge computing architecture for task offloading optimization [J]. Journal of Computer Applications, 2026, 46(8): 2524-2532.
[4]	Xuan CUI, Bo LIU. Unsupervised face attribute editing method based on dynamic convolutional autoencoder [J]. Journal of Computer Applications, 2026, 46(4): 1300-1308.
[5]	Min CHEN, Xiaolin QIN, Shaohan LI, Hao YANG, Taohong LI. Review of deep learning applications in severe convective weather prediction [J]. Journal of Computer Applications, 2026, 46(3): 980-992.
[6]	Bing GAO, Jinzhuo LIN, Qijie ZOU, Yongqiang YAO. Zero-shot knowledge graph relation prediction method via dual-channel embedding fusion [J]. Journal of Computer Applications, 2026, 46(10): 3117-3123.
[7]	Yinlong JIAN, Xuebin CHEN, Zhongrui JING, Qi ZHONG, Zhenbo ZHANG. Data augmentation scheme based on conditional generative adversarial network in federated learning [J]. Journal of Computer Applications, 2026, 46(1): 21-32.
[8]	Na FAN, Chuang LUO, Zehui ZHANG, Mengyao ZHANG, Ding MU. Semantic privacy protection mechanism of vehicle trajectory based on improved generative adversarial network [J]. Journal of Computer Applications, 2026, 46(1): 169-180.
[9]	Lifang WANG, Wenjing REN, Xiaodong GUO, Rongguo ZHANG, Lihua HU. Trident generative adversarial network for low-dose CT image denoising [J]. Journal of Computer Applications, 2026, 46(1): 270-279.
[10]	Yilin DENG, Fajiang YU. Pseudo random number generator based on LSTM and separable self-attention mechanism [J]. Journal of Computer Applications, 2025, 45(9): 2893-2901.
[11]	Jin ZHOU, Yuzhi LI, Xu ZHANG, Shuo GAO, Li ZHANG, Jiachuan SHENG. Modulation recognition network for complex electromagnetic environments [J]. Journal of Computer Applications, 2025, 45(8): 2672-2682.
[12]	Ying HUANG, Shengmei GAO, Guang CHEN, Su LIU. Low-light image enhancement network combining signal-to-noise ratio guided dual-branch structure and histogram equalization [J]. Journal of Computer Applications, 2025, 45(6): 1971-1979.
[13]	Tianyu XUE, Aiping LI, Liguo DUAN. Vehicular edge computing scheme with task offloading and resource optimization [J]. Journal of Computer Applications, 2025, 45(6): 1766-1775.
[14]	Yiming ZHANG, Tengfei CAO. Federated learning optimization algorithm based on local drift and diversity computing power [J]. Journal of Computer Applications, 2025, 45(5): 1447-1454.
[15]	Hui LI, Bingzhi JIA, Chenxi WANG, Ziyu DONG, Jilong LI, Zhaoman ZHONG, Yanyan CHEN. Generative adversarial network underwater image enhancement model based on Swin Transformer [J]. Journal of Computer Applications, 2025, 45(5): 1439-1446.