Integrated information system based on Q-learning algorithm and multi-objective particle swarm optimization with molecular fuzzy-based decision-making for corporate environmental investments
Determining the most important criteria is a great necessity to increase the environmental performance of renewable energy projects. This situation helps to reach cost efficiency and effective use of limited resources. However, there are very few studies in the literature where priority analysis is...
Gespeichert in:
| Veröffentlicht in: | Information sciences Jg. 698; S. 121757 |
|---|---|
| Hauptverfasser: | , , , |
| Format: | Journal Article |
| Sprache: | Englisch |
| Veröffentlicht: |
Elsevier Inc
01.04.2025
|
| Schlagworte: | |
| ISSN: | 0020-0255 |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| Zusammenfassung: | Determining the most important criteria is a great necessity to increase the environmental performance of renewable energy projects. This situation helps to reach cost efficiency and effective use of limited resources. However, there are very few studies in the literature where priority analysis is made for these factors. This condition indicates an important gap in the literature on this subject. Accordingly, this study aims to identify the most convenient investment strategies to increase the environmental performance of renewable energy projects. First, the balanced expert dataset is generated via Q-learning algorithm and multi-objective particle swarm optimization. In the following step, selected criteria are weighted with molecular fuzzy cognitive maps approach. The final stage consists of ranking the alternatives with fuzzy molecular ranking (MORAN). The contribution of this study to the literature is to define the most appropriate investment strategies to increase the environmental performance of these projects by generating a new decision-making model. Integrating molecular geometry into decision-making processes increases both the originality and effectiveness of the model. Thus, it is possible to calculate the degrees with a more scientific infrastructure. Integrating Q-learning and swarm optimization techniques into the decision-making model also increases the superiority of the model. In this context, the optimization technique is used to obtain the importance weights of the experts. The findings denote that energy capacity expansion plays the most important role in improving the environmental performance of businesses because it has the greatest weight (0.2563). Return on investment is another factor that plays an important role in increasing this performance with the weight of 0.2559. Geothermal and hydropower are found as the most successful renewable energy types regarding environmental performance improvement since they have the highest aggregated values (0.534 and 0.620). Carbon tax is an important policy application to increase renewable energy capacity. With the help of this tax, fossil fuels lose their competitive advantage significantly. As a result, this situation has a positive contribution to the increase of the renewable energy projects. |
|---|---|
| ISSN: | 0020-0255 |
| DOI: | 10.1016/j.ins.2024.121757 |