Digital twins are increasingly applied in microgrid energy systems to support real-time monitoring, predictive control, and operational decision-making. However, the sustainability implications of such applications—particularly when integrating artificial intelligence (AI) and renewable energy sources—remain insufficiently explored from a life-cycle perspective. This study develops a multi-criteria evaluation framework based on the Vector-Based Preference Aided Ranking System (V-PARS) to systematically assess four AI-driven digital twin implementation alternatives in microgrid energy management. Expert-Determined sustainability, reliability, and performance indicators, encompassing technical, economic, and environmental dimensions, are employed to capture the trade-offs associated with each configuration. The research investigates how AI-integrated digital twins influence energy distribution efficiency, operational resilience, and environmental performance within microgrids, offering a balanced assessment without overemphasizing any single criterion. By providing a structured decision-support framework, this work contributes to the literature on sustainable digitalization of microgrids and supports policymakers and system designers in aligning intelligent energy infrastructures with low-carbon and resource-efficient objectives.
ESRA ÇAKIR (2025) studied this question.