Cluster-based decision making: a novel approach for handling large-scale alternatives in rooftop solar PV site selection

Cluster-based decision making: a novel approach for handling large-scale alternatives in rooftop solar PV site selection

연구 분야: Verification

학회: Artificial Intelligence Review

This research proposes to develop a systematic methodology for ranking a large number of alternatives in large-scale real-world problems under uncertainty, where the traditional individual ranking methods fail to provide meaningful and actionable insights. This paper introduces a novel framework for fuzzy large-scale decision-making (FLSDM) using triangular neutrosophic fuzzy numbers (TNFNs) to perform cluster-based ranking as a solution to these challenges. The proposed approach develops the Sugeno–Weber operator within the TNFN environment for data aggregation. An advanced K-means++ algorithm is designed to enable precise clustering of alternatives. Using the TOPSIS and DEA cross-efficiency model, extended for TNFNs, the clusters are ranked, and the alternatives are prioritized within each cluster. The practical use of the proposed approach is demonstrated through a real-world case study on rooftop solar photovoltaic (PV) site selection. Additionally, thorough analyses are conducted to validate its robustness and effectiveness.