AI-Driven Hybrid Fuzzy MCDM Framework for Sustainable Renewable Energy Source Selection under Uncertainty

In this paper, we propose a framework based on Artificial Intelligence (AI) that integrates Hybrid Fuzzy Analytic Hierarchy Process (F-AHP) and Fuzzy Technique for Order Preference by Similarity to Ideal Solution (F-TOPSIS) for the selection of renewable energy sources in uncertain and dynamic decision making environments. The choice of appropriate renewable energy options such as solar, wind, biomass and hydro is associated with many trade issues, such as economic, environmental, technological, reliability and social acceptability. The inherent vagueness and subjectivity of these factors lead to a very complex and challenging decision-making process. The proposed framework blends fuzzy logic with machine learning methods to emulate human judgements accurately and to deal with ambiguity in expert evaluations. Fuzzy logic, by using membership functions, enables the translation of linguistic assessments into mathematical expressions, reflecting the ambiguity and imprecision of decision makers’ preferences. The use of AI algorithms allows for the dynamic modification of criteria weights by analysing historical data, expert knowledge and changing environmental circumstances. The proposed adaptive weighting scheme significantly improves the resilience and reliability of the decision-making process compared to existing MCDM approaches based on static weights and deterministic assumptions. The suggested hybrid F-AHP–TOPSIS technique determines the relative importance of assessment criteria using fuzzy pairwise comparisons and ranks the renewable energy options according to their distances from the ideal and anti-ideal solutions. AI also brings the ability to process data in real time, extract information automatically and continually refine the parameters that drive decisions. Thus, the proposed model offers an intelligent, flexible and scalable decision support system, which performs well in uncertain and fast changing environments. The proposed paradigm has major implications on sustainable energy planning and policy formulation by helping decision makers select best possible renewable energy resources considering economic, environmental and social objectives. The framework’s flexibility and generalisability allow for its use in a wide range of sectors, such as: healthcare resource allocation, smart city infrastructure planning, transport management, supply chain optimisation, and Industry 5.0 systems. The integration of AI with fuzzy MCDM techniques provides a promising direction for developing next-generation intelligent decision-support systems to address complex multi-criteria problems under ambiguity.

1. Kumar, A.; Singh, P.; Kacher, Y. Neutrosophic hyperbolic programming strategy for uncertain multi-objective transportation problem. Appl. Soft Comput. 2023, 149, 110949. [Google Scholar] [CrossRef] 2. Yu, Q.; Yang, C.; Dai, G.; Peng, L.; Li, J. A novel penalty function-based interval constrained multi-objective optimization algorithm for uncertain problems. Swarm Evol. Comput. 2024, 88, 101584. [Google Scholar] [CrossRef] 3. Kumar, S.; Mahato, N.K.; Ghosh, D. Solution of Uncertain Multiobjective Optimization Problems by Using Nonlinear Conjugate Gradient Method. arXiv 2025, arXiv:2503.00311. [Google Scholar] [CrossRef] 4. Guo, D.; Wang, X.; Gao, K.; Jin, Y.; Ding, J.; Chai, T. Evolutionary Optimization of High-Dimensional Multiobjective and Many-Objective Expensive Problems Assisted by a Dropout Neural Network. IEEE Trans. Syst. Man Cybern. Syst. 2022, 52, 2084–2097. [Google Scholar] [CrossRef] 5. Myakala, P.K.; Jonnalagadda, A.K.; Naayini, P. Revolutionizing Big Data with AI-Driven Hybrid Soft Computing Techniques. Mach. Learn. Appl. Int. J. 2025, 12, 1–13. [Google Scholar] [CrossRef] 6. Valdez, F.; Melin, P.; Castillo, O. Evolutionary method combining particle swarm optimization and genetic algorithms using fuzzy logic for decision making. In Proceedings of the 2009 IEEE International Conference on Fuzzy Systems, Jeju, Republic of Korea, 20–24 August 2009; pp. 2114–2119. [Google Scholar] [CrossRef] 7. Urbańczyk, P.; Urbańczyk, A.; Król, M.; Rutkowski, L.; Kisiel-Dorohinicki, M. Sequential, Parallel and Consecutive Hybrid Evolutionary-Swarm Optimization Metaheuristics. arXiv 2025, arXiv:2508.00229. [Google Scholar] [CrossRef] 8. Lughofer, E. Evolving multi-user fuzzy classifier systems integrating human uncertainty and expert knowledge. Inf. Sci. 2022, 596, 30–52. [Google Scholar] [CrossRef] 9. Zhang, Y. Review of evolutionary computation. Proc. SPIE 2025, 13562, 1356232. [Google Scholar] [CrossRef] 10.       Al-Himyari, B.; Al-khafaji, H.; Hussain, N.F. Exploration-Exploitation Tradeoffs in Metaheuristics: A Review. Asian J. Appl. Sci. 2025, 12, 1–21. [Google Scholar] [CrossRef]