Optimal Electric Vehicle Charging Location Selection Using a Linguistic Neural Network Approach

In this article, we present two novel hybrid decision-making models for solving multi-criteria group decision-making (MCGDM) problems, with a focus on selecting optimal electric vehicle charging station (EVCS) locations. The proposed models integrate the linguistic TOPSIS method with a linguistic pq -rung orthopair fuzzy neural network (L pq -ROFNN) and sine trigonometric aggregation operators to effectively model uncertainty and linguistic assessments in complex decision-making environments. To support the proposed framework, we develop score and accuracy functions, a distance measure, and a set of linguistic pq -rung orthopair sine trigonometric fuzzy weighted aggregation operators for effective evaluation and ranking of alternatives. The proposed combined decision-making model is applied to a real-world EVCS location selection problem. The results indicate that the Residential Community Center ( \({\mathfrak{H}}_{1}\) ) is the most suitable location for an EV charging station. This site offers a balanced combination of moderate traffic and low installation costs, making it an economically practical choice. A sensitivity analysis is conducted to examine the influence of key parameters on the decision outcomes, demonstrating the robustness and consistency of the proposed model. Furthermore, a comparative analysis with multi-criteria decision-making (MCDM) methods confirms the effectiveness of the proposed approach. Overall, the proposed framework provides an accurate, flexible, and reliable decision-support tool for EV charging station planning under uncertainty, contributing to the advancement of sustainable transportation systems.