Graph Neural Network-Based Digital Twin for Cyber-Resilient and Predictive Teleoperation Systems

Mahmoudi Rashid, Sara

doi:10.22044/jadm.2025.16223.2747

Document Type : Original/Review Paper

Author

Sara Mahmoudi Rashid

Faculty of Electrical and Computer Engineering, University of Tabriz, Tabriz, Iran.

https://doi.org/10.22044/jadm.2025.16223.2747

Abstract

Teleoperation systems are increasingly deployed in critical applications such as robotic surgery, industrial automation, and hazardous environment exploration. However, these systems are highly susceptible to network-induced delays, cyber-attacks, and system uncertainties, which can degrade performance and compromise safety. This paper proposes a Graph Neural Network (GNN)-based Digital Twin (DT) framework to enhance the cyber-resilience and predictive control of teleoperation systems. The GNN-based anomaly detection mechanism accurately identifies cyber-attacks, such as false data injection (FDI) and denial-of-service (DoS) attacks, with a detection rate of 24.3% and a false alarm rate of only 1.8%, significantly outperforming conventional machine learning methods. Furthermore, the predictive digital twin model, integrated with model predictive control (MPC), effectively compensates for latency and dynamic uncertainties, reducing control errors by 14.12% compared to traditional PID controllers. Simulation results in a robotic teleoperation testbed demonstrate a 24.4% improvement in trajectory tracking accuracy under variable delay conditions, ensuring precise and stable operation.

Keywords

Main Subjects

H.3. Artificial Intelligence

References

[1] S. Ghandibidgoli and H. Mokhtari, "Automatic control and guidance of mobile robot using machine learning methods," J Journal of AI Data Mining, vol. 10, no. 3, pp. 385-400, 2022.

[2] F. Sabahi, "Stable Synchronization in Fuzzy Recurrent Neural Networks within a Fixed Time Frame," J Journal of AI Data Mining, vol. 12, no. 4, pp. 545-566, 2024.

[3] P. S. Tadepalli, D. Pullaguram, and M. Alam, "Cyber-Resilient Strategy for DC Microgrids Against Concurrent FDI and DoS Attacks," J IEEE Transactions on Industrial Informatics, vol. 21, no. 6, pp. 4756 - 4767, 2025.

[4] Ramesh, M., and R. Jayashree. "Adaptive E-Learning Environments: A Methodological Approach to Identifying and Integrating Multi-layered Learning Styles." SN Computer Science, vol. 5, no. 6, pp. 772, 2024.

[5] P. Rabiei and N. Ashrafi-Payaman, "Anomaly Detection in Dynamic Graph Using Machine Learning Algorithms," J Journal of AI Data Mining, vol. 12, no. 3, pp. 359-367, 2024.

[6] G. Wu, H. Zhang, W. Wu, Y. Wang, and Z. Wu, "Physics-Informed Graph Convolutional Recurrent Network for Cyber-Attack Detection in Chemical Process Networks," J Industrial Engineering Chemistry Research, vol. 64, no. 6, pp. 3370-3382, 2025.

[7] L. Rojas, Á. Peña, and J. Garcia, "AI-Driven Predictive Maintenance in Mining: A Systematic Literature Review on Fault Detection, Digital Twins, and Intelligent Asset Management," J Applied Sciences, vol. 15, no. 6, p. 3337, 2025.

[8] M.-Z. Pan, J.-A. Li, Z. Li, K. Liang, T.-C. Su, K. Liang, and G.-B. Bian, "A Graph Robot Network for Force Observer of Teleoperation Systems," J IEEE/ASME Transactions on Mechatronics, vol. 30, no. 1, pp. 530-540, 2024.

[9] M. S. Abdelrahman, I. Kharchouf, H. M. Hussein, M. Esoofally, and O. A. Mohammed, "Enhancing Cyber-Physical Resiliency of Microgrid Control under Denial-of-Service Attack with Digital Twins," J Energies, vol. 17, no. 16, p. 3927, 2024.

[10] S. Wang, X. Xiang, J. Zhang, Z. Liang, S. Li, P. Zhong, J. Zeng, and C. Wang, "A Multi-Task Spatiotemporal Graph Neural Network for Transient Stability and State Prediction in Power Systems," J Energies, vol. 18, no. 6, p. 1531, 2025.

[11] L. Xiao, H. Chen, S. Xu, Z. Lv, C. Wang, and Y. Xiao, "Reinforcement Learning-Based False Data Injection Attacks in Smart Grids," J IEEE Transactions on Industrial Informatics, vol. 21, no. 4, pp. 3475-3484.

[12] I. Varlamis, Y. Himeur, C. Chronis, and C. Sardianos, "Blockchain technology for secure digital twin data management," J Blockchain and Digital Twin for Smart Healthcare, 2025, pp. 439-452.

[13] Q. Liu, L. Pan, X. Cao, J. Gan, X. Huang, X. J. C. Liu, C. Practice, and Experience, "A spatio‐temporal graph convolutional approach to real‐time load forecasting in an edge‐enabled distributed Internet of Smart Grids energy system," J Concurrency Computation: Practice Experience, vol. 36, no. 13, p. e8060, 2024.

[14] Y. Zhang, C. Du, Z. Chen, Z. Feng, and W. Gui, "Digital Twin-Based Resilient Model Predictive Control for Industrial Cyber-Physical Systems," J IEEE Journal of Emerging Selected Topics in Industrial Electronics, vol. 6, no. 4, pp. 1853-1862, 2025.

[15] N. Ehmann, M. Köhler, and F. Allgöwer, "Transient performance of MPC for tracking without terminal constraints," J IEEE Control Systems Letters, vol. 9, no. 4, pp. 1456-2475, 2025.

[16] F. Zhao, F. Dörfler, A. Chiuso, and K. You, "Data-enabled policy optimization for direct adaptive learning of the LQR," J IEEE Transactions on Automatic Control, vol. 70, no. 11, pp. 7211-7232, 2025.

[17] S. A. Aessa, S. W. Shneen, and M. K. Oudah, "Optimizing PID Controller for Large-Scale MIMO Systems Using Flower Pollination Algorithm," J Journal of Robotics Control, vol. 6, no. 2, pp. 553-559, 2025.

[18] Z. Liu, Y. Wang, Q. Wang, and M. Hu, "Vision transformer-based anomaly detection in smart grid phasor measurement units using deep learning models," J IEEE Access, vol. 13, no. 2, pp. 44565-44576, 2025.

[19] S. Pavani and H. Shwehta, "Hybrid Deep Learning for Financial Forecasting: Integrating LSTM and GNN for Enhanced Stock Price Prediction."

[20] M. Ahmadi, H. Aly, and M. Khashei, "Enhancing power grid stability with a hybrid framework for wind power forecasting: Integrating Kalman Filtering, Deep Residual Learning, and Bidirectional LSTM," J Energy,

vol. 334, no. 8, p. 137752, 2025.