Q-learning algorithm and molecular fuzzy multi-objective particle swarm optimization-based decision-making approach to circular economy-oriented investment alternatives for renewable energy technologies

• Published in: Information sciences Vol. 718; p. 122378
• Main Authors: Dinçer, Hasan, Yüksel, Serhat, Eti, Serkan, Olaru, Gabriela Oana, Deveci, Muhammet, Wu, Qun, Castillo, Oscar
• Format: Journal Article
• Language: English
• Published: Elsevier Inc 01.11.2025
• Subjects: Molecular fuzzy sets; Multi-objective particle swarm optimization; Q-learning algorithm; Renewable energy technologies; Multi-objective particle swarm optimization; Renewable energy technologies; Molecular fuzzy sets; Q-learning algorithm
• ISSN: 0020-0255
• DOI: 10.1016/j.ins.2025.122378

Determining the most critical performance indicators of renewable energy technology investments is necessary for different purposes, such as successful strategic planning and correct identification and management of risks. However, there are limited studies in the literature in this context. This issue demonstrates that there is a significant gap in the literature on this subject. Accordingly, the purpose of this study is to identify effective investment strategies to improve renewable energy technologies. The first stage is related to the constructing the balanced expert dataset using Q-learning algorithm. The next stage consists of weighting the criteria with molecular fuzzy cognitive maps. The final section ranks the alternatives with molecular fuzzy multi-objective particle swarm optimization. The main contribution of this study is the optimization of investment strategies with a novel decision-making model. Integration of molecular geometry into multi-criteria decision-making analysis provides various advantages, especially in modelling complex systems, such as more effective uncertainty management and implication the normalization process better. The findings denote that innovative solutions are determined as the most important criterion in increasing the performance of renewable energy technologies. Lifecycle efficiency is another important variable in increasing the performance of renewable energy technologies. Moreover, developing circular models of decentralized energy systems is found as the most essential circular economy-oriented investment alternative for renewable energy technologies.