The increasing complexity of modern urban power systems, combined with growing requirements for reliability, resilience, and situational awareness, necessitates the development of advanced monitoring and decision-support technologies. Digital twin technology has emerged as a promising approach for creating synchronized virtual representations of physical infrastructure capable of supporting real-time analysis, prediction, and operational management. This work presents an AI-supported digital twin platform for urban power grid monitoring developed on the basis of a digital substation testbed compliant with modern smart grid principles. The proposed platform integrates a physical digital substation model, supervisory control and data acquisition infrastructure, intelligent electronic devices, communication networks, and a real-time digital twin environment implemented in ANSYS Twin Builder. A bidirectional data exchange mechanism is established between the physical and virtual domains, enabling continuous synchronization of operating parameters and system states. The architecture supports the acquisition, processing, and storage of operational data, as well as the execution of predictive simulations under normal and emergency operating conditions. The obtained results demonstrate the feasibility of combining digital substation technologies, real-time digital twins, and artificial intelligence within a unified framework for urban power grid monitoring. The proposed approach contributes to the development of next-generation intelligent energy management systems and creates a scalable experimental environment for future research in power system reliability, resilience, and critical infrastructure protection.
Pliuhin et al. (Thu,) studied this question.