AI-Enabled Digital Twins for Smart Grids: RealTime Monitoring, Predictive Control, Cybersecurity and Future Research Directions

Abstract

Digital twin (DT) technology combined with artificial intelligence (AI) is becoming a key enabler for resilient and self-optimising electrical power networks that are increasingly digitalised. A digital twin is a continuously updated virtual representation of a physical grid asset or network that uses real-time sensor, phasor measurement unit (PMU), and Internet of Things (IoT) data to closely mirror its physical counterpart. Digital twins become predictive, prescriptive, and self-healing decision-support systems when machine learning (ML) and deep learning (DL) algorithms are integrated into this virtual-physical feedback loop. This review aims to bring together the recent literature (2020-2025) on the field of AIpowered digital twins under four thematic areas: (i) architectural foundations and enabling technologies, (ii) real-time monitoring and state estimation, (iii) predictive control and maintenance, and (iv) cybersecurity monitoring and threat mitigation. Tables summarise enabling technologies, predictive-control case studies, and case studies of cyber-threat countermeasures reported in the literature. The review also pinpoints open research challenges such as interoperability standards, federated and privacypreserving learning, explainability of AI-driven decisions on the grid, and quantum-assisted twin computation. It suggests a research roadmap for further work. The synthesis signals that while AI-powered digital twins can tangibly reduce unplanned downtime, improve forecasting precision, and boost cyberphysical attack resilience, standardisation, data governance, and trustworthy AI remain to be addressed to enable widespread adoption.