Integrating Fuzzy-Machine Learning and Bibliometric Analysis for SDG-Aligned Renewable Energy Strategies

Abstract

This research aims to analyze and predict the most suitable renewable energy source using a machine learning model aligned with the Sustainable Development Goals (SDGs). A bibliometric analysis is conducted to select relevant literature from Scopus and Web of Science databases to identify key sustainability criteria. The criteria weights are determined using the fuzzy Analytical Hierarchy Process (AHP), while prediction is performed using a logistic regression model combined with fuzzy TOPSIS. This approach ensures a data-driven selection of renewable energy sources. The results highlight ‘Technological Innovation’ as the most critical criterion, while ‘Concentrating Solar’ emerges as the best-suited renewable energy option. The proposed model offers a structured framework to aid policy-makers in selecting appropriate renewable energy solution for different regions. This study provides a systematic decision-making model for renewable energy selection, incorporating advanced machine learning and fuzzy MCDM techniques. Future research can explore additional machine learning models to enhance prediction accuracy and decision-making efficiency.