Analyzing energy transition for industry 4.0-driven hybrid energy system selection with advanced neural network-used multi-criteria decision-making technique

This study aims to select the appropriate renewable energy alternatives for the efficiency of hybrid energy systems to increase energy transition performance. For this purpose, a novel neural network (NN)-based fuzzy decision-making model is constructed that has three different stages. In the first stage, NN-based fuzzy decision matrix is created. Secondly, 6 different variables based on industry 4.0 are weighted with the sine trigonometric Pythagorean fuzzy entropy technique. Additionally, another calculation has been implemented with criteria importance through intercriteria correlation (CRITIC) to identify the consistency of the results. Furthermore, in the third stage, considering 5 different renewable energy alternatives, 10 different combinations are identified for hybrid energy systems. The most effective alternatives are defined by the sine trigonometric Pythagorean fuzzy ranking technique by geometric mean of similarity ratio to optimal solution (RATGOS) method. Moreover, to test the validity of these results, another analysis is conducted using the additive ratio assessment (ARAS) technique. The main contribution of the study is that the optimal renewable energy combination required for an efficient hybrid energy system is determined by performing a priority analysis between the variables. This situation has a significant guiding feature for investors. Similarly, the development of the RATGOS technique both increases the methodological originality of the study and enables more accurate alternative ranking. It is identified that the results of all methods are similar. Therefore, this situation gives information about the coherency and validity of the findings. It is concluded that the most important criterion is real-time capability. It is also denoted that the best combination for hybrid energy systems is Solar-Wind.