• Energy Research

It is widely accepted that there is an urgent need to make green hydrogen (GH2) projects financially viable to reduce global warming. However, any form of improvements to these GH2 projects lead to substantial cost increase. Due to this cost increase, making many improvements negatively affects the financial profitability of hydrogen projects. This is why there is a need for new advanced financial priority analysis tools so that it is easier to develop GH2 projects globally. Accordingly, the aim of this study is to identify and then define the most important factors affecting GH2 generation projects. To achieve this aim, this work proposes a new fuzzy multi-criteria decision-making model based on artificial intelligence (AI). First, experts are weighted with AI technique. Second, the missing evaluations are filled via a recommender system. Third, criteria weights are calculated by the M-SWARA technique integrated with quantum picture fuzzy rough (QPFR) sets. Finally, GH2 energy generation processes are listed by the QPFR-VIKOR approach. Overall, the main contribution of this study is the generation of a comprehensive AI oriented fuzzy decision-making model to make a detailed evaluation with respect to the financial potential improvements of the GH2 generation projects. The main originality of this model is the consideration of AI to calculate the weights of the criteria. Similarly, another benefit of the proposed model, that increases its superiority against other models, is the completion of missing evaluations by experts thanks to the recommender system. It is concluded that the most important criterion affecting green hydrogen investments is organizational effectiveness.

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.