Home / Current Issue / Paper 1719424
Digital Twin-Based Predictive Maintenance and Voltage Stability Enhancement of Distribution Networks with High Solar PV Penetration Using Artificial Intelligence
Subject area: Science,Engineering and Technology · Area of research: Electrical and Electronic Engineering
DOI: https://doi.org/10.64388/IREV10I1-1719424
Abstract
The integration of solar photovoltaic (PV) systems into electrical distribution networks introduces challenges such as voltage fluctuations, increased equipment stress, and reduced system reliability. This study presents a Digital Twin-based framework for predictive maintenance and voltage stability enhancement in PV-rich distribution networks using Artificial Intelligence (AI) .The proposed framework combines a real-time digital twin with machine learning models to continuously monitor system conditions, predict equipment failures, and detect abnormal operating states from voltage profiles, load variations, and asset health indicators. An adaptive voltage regulation scheme is also implemented to maintain acceptable voltage limits under high PV penetration and dynamic loading. Simulation results show that the proposed method reduces voltage deviation by 18–25%, maintains bus voltages within 0.95–1.05 p u., and decreases system power losses by 12–20% compared to conventional methods. In addition, predictive maintenance improves fault detection accuracy to 92–97%, reduces unexpected outages by 20–35%, and lowers maintenance costs by 15–28%. Overall, the results demonstrate that integrating digital twin and AI techniques significantly enhances voltage stability, system reliability, and operational efficiency in modern PV-integrated distribution networks.
Keywords
Digital Twin, Artificial Intelligence, Predictive Maintenance, Voltage Stability, Solar Photovoltaic Systems, Distribution Networks, Smart Grid, Renewable Energy Integration.
How to cite this paper
@article{1719424,
author = {Chukwuemeka, S. N., Anigbogu, C. C., Benjamin, A. O. E., Ezenwa, K. I.},
title = {Digital Twin-Based Predictive Maintenance and Voltage Stability Enhancement of Distribution Networks with High Solar PV Penetration Using Artificial Intelligence},
journal = {Iconic Research And Engineering Journals},
year = {2026},
volume = {10},
number = {1},
pages = {423-431},
issn = {2456-8880},
url = {https://www.irejournals.com/formatedpaper/1719424.pdf},
abstract = {The integration of solar photovoltaic (PV) systems into electrical distribution networks introduces challenges such as voltage fluctuations, increased equipment stress, and reduced system reliability. This study presents a Digital Twin-based framework for predictive maintenance and voltage stability enhancement in PV-rich distribution networks using Artificial Intelligence (AI) .The proposed framework combines a real-time digital twin with machine learning models to continuously monitor system conditions, predict equipment failures, and detect abnormal operating states from voltage profiles, load variations, and asset health indicators. An adaptive voltage regulation scheme is also implemented to maintain acceptable voltage limits under high PV penetration and dynamic loading. Simulation results show that the proposed method reduces voltage deviation by 18–25%, maintains bus voltages within 0.95–1.05 p u., and decreases system power losses by 12–20% compared to conventional methods. In addition, predictive maintenance improves fault detection accuracy to 92–97%, reduces unexpected outages by 20–35%, and lowers maintenance costs by 15–28%. Overall, the results demonstrate that integrating digital twin and AI techniques significantly enhances voltage stability, system reliability, and operational efficiency in modern PV-integrated distribution networks. },
keywords = {Digital Twin, Artificial Intelligence, Predictive Maintenance, Voltage Stability, Solar Photovoltaic Systems, Distribution Networks, Smart Grid, Renewable Energy Integration. },
month = {July},
doi = {https://doi.org/10.64388/IREV10I1-1719424}
}