An Internet of Things Integrated Deep Graph Learning for Real-Time Voltage Stability Prediction in Electrical Distribution Networks: A Comprehensive Review

Ganiyu Adedayo Ajenikoko; Adeolu Olawuni

doi:10.56201/ijemt.vol.11.no12.2025.pg17.21

📄 Download Paper

An Internet of Things Integrated Deep Graph Learning for Real-Time Voltage Stability Prediction in Electrical Distribution Networks: A Comprehensive Review

Ganiyu Adedayo Ajenikoko, Adeolu Olawuni

Abstract

Voltage instability has emerged as one of the most persistent threats to the reliability of modern electrical distribution networks. Traditional analytical and numerical methods are limited in handling the increasingly complex and data-rich environment of smart grids. Recent advances in artificial intelligence particularly the integration of Internet of Things (IoT) technology and deep graph learning offer new possibilities for real-time voltage stability monitoring and prediction. This review examines the state-of-the-art developments in IoT-integrated deep graph learning frameworks for voltage stability prediction in distribution networks. It explores how graph-based neural architectures capture spatial-topological dependencies of grid components, how IoT sensor networks enable real-time data acquisition, and how hybrid learning models enhance prediction accuracy. The paper highlights methodological innovations, implementation challenges, and key research gaps, with a focus on practical deployment within emerging power systems.

Keywords

Internet of ThingsDeep Graph LearningVoltage StabilitySmart Distribution NetworksPredictive Modelingspatial-technological dependencies

References

Ahmed, S., & Olagunju, O. (2023). Long-term voltage stability forecasting using hybrid graph convolutional networks. Journal of Electrical Engineering, 45(2), 112-125. Chakraborty, S., et al. (2021). Voltage stability in distribution networks: A review. Renewable and Sustainable Energy Reviews, 145, 111025. Chen, R., Wang, L., & Lin, P. (2023). Deep graph learning in power system stability analysis: A survey. Energies, 16(8), 3415. Lawal, M. A., Eze, C. J., & Ogunbiyi, T. B. (2024). IoT-enabled machine learning framework for predictive voltage control in distribution feeders. Smart Grid and Renewable Energy, 15(3), 167-182. Liu, D., Zhang, H., & Xu, Y. (2022). Real-time voltage stability margin assessment using graph convolutional networks. IEEE Transactions on Smart Grid, 13(5), 4134-4144. Ma, Y., Zhou, T., & Chen, S. (2022). A spatio-temporal graph neural network approach for voltage prediction in smart grids. Energy Reports, 8, 947-960. Okafor, E. O., Balogun, A. A., & Adebayo, J. T. (2024). Edge-assisted IoT framework for smart grid voltage monitoring in emerging economies. Journal of Electrical Systems and Information Technology, 11(1), 44-59. Wang, Z., & Huang, Y. (2023). Internet of Things and deep graph learning for smart grid applications. IEEE Internet of Things Journal, 10(12), 10567-10580. Xu, Y., et al. (2023). IoT-based voltage stability monitoring using deep learning. IEEE Transactions on Industrial Informatics, 19(4), 3456-3465.

An Internet of Things Integrated Deep Graph Learning for Real-Time Voltage Stability Prediction in Electrical Distribution Networks: A Comprehensive Review

Abstract

Keywords

References

More Articles from INTERNATIONAL JOURNAL OF ENGINEERING AND MODERN TECHNOLOGY