A hybrid decision-support framework for EV charging station selection: Integrating subjective, objective, and data-driven weighting

This study proposes an integrated decision-support framework for selecting electric vehicle (EV) charging stations in smart city environments. The framework combines multi-criteria decision-making (MCDM) and data-driven techniques to evaluate charging alternatives based on key operational factors, including travel time, waiting time, charging duration, energy price, and required energy. Unlike conventional approaches that rely on a single weighting mechanism, the proposed framework incorporates three complementary weighting paradigms: subjective (Fuzzy AHP), objective (Grey Relational Analysis), and data-driven (K-Means++). These weights are subsequently embedded into multiple ranking mechanisms, enabling a flexible, adaptive evaluation process. The results demonstrate that different weighting paradigms yield structurally distinct decision outcomes, revealing critical trade-offs among user preferences, system efficiency, and data-driven patterns. This highlights the importance of selecting an appropriate weighting strategy depending on the decision context. The proposed framework is computationally efficient, scalable, and adaptable, making it suitable for decision support, using real-time snapshots of charging-network conditions, and for smart mobility applications. It provides practical insights for designing user-centric and data-aware charging strategies in next-generation urban energy systems.