AI-Assisted Digital Twin Framework for Virtual Resilience Assessment and Scalable Planning of Rural Hybrid Microgrids
Contributors
Dr Anurag S D Rai
Shashi Kant Gupta
Keywords
Proceeding
Track
General Track
License
Copyright (c) 2026 Sustainable Global Societies Initiative

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
Abstract
Rural hybrid microgrids operate under variable solar availability, changing load demand, battery degradation and limited maintenance support, making conventional site-specific performance assessment insufficient for long-term resilience planning. This paper presents an AI-assisted Digital Twin framework for converting an operational rural hybrid microgrid into a calibrated virtual representation for resilience assessment and scalable planning. The framework uses the physical configuration, operational data and energy-flow characteristics of an existing microgrid to develop a virtual model, followed by AI-assisted analysis of load behaviour, renewable generation patterns and operational variability. Virtual stress scenarios can subsequently be applied without physically modifying the deployed system. The methodology is demonstrated using three operational 3 kW solar-battery hybrid microgrids deployed in Harshdiwari, Kanarkheda and Mudpar in Central India. Existing operational results show renewable fractions of 97.9–100%, unmet load below 1.05% and approximately 1.5 days of battery autonomy. These deployments provide the empirical foundation for Digital Twin development and scenario-based resilience assessment. The proposed framework establishes a practical pathway from physical deployment to calibrated Digital Twin, virtual stress testing and scalable microgrid planning.