A novel integrated energy system evaluation method using molecular fuzzy cognitive maps and multi-objective grey wolf optimization

The development of integrated energy systems (IESs) has become a strategic priority for achieving sustainable global energy and economic growth. Prior to implementation, alternative IES schemes must be rigorously evaluated to identify the most suitable option. However, subjective weighting methods often suffer from arbitrariness, whereas objective methods may fail to capture subtle variations in the evaluation matrix. To address these limitations, this study proposes a novel combination weighting approach that integrates molecular fuzzy cognitive maps (MFCM) with multi-objective grey wolf optimization (MOGWO) to determine comprehensive index weights. Subjective weights are derived from MFCM, while objective weights are obtained using the anti-entropy weighting (AEW) method. A multi-objective optimization model is then formulated to minimize deviations among subjective, objective, and combined weights, as well as the intra-cluster dispersion of schemes. The model is solved using MOGWO, and the technique for order preference by similarity to ideal solution is employed to rank IES schemes. Experiments on two real-world datasets demonstrate that the proposed method achieves superior accuracy and robustness compared with conventional approaches. The main contributions of this study are as follows: (1) a novel combination weighting method integrating MFCM-based subjective weighting with AEW-based objective weighting to balance expert knowledge and data-driven objectivity; (2) construction of a multi-objective optimization model for combined weights, solved by MOGWO to obtain an optimal Pareto solution set; and (3) validation of the effectiveness and superiority of the proposed method through comparative experiments on real-world datasets.