AI-driven energy management system based on hesitant bipolar complex fuzzy Hamacher power aggregation operators and their applications in MADM
Abstract Artificial Intelligence (AI) based energy management systems utilize sophisticated AI algorithms to improve and control the consumption of energy in various sectors, such as power utilities, industrial systems, and smart buildings. These systems support real-time analysis of data, predictiv...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-04-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-025-94340-3 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Abstract Artificial Intelligence (AI) based energy management systems utilize sophisticated AI algorithms to improve and control the consumption of energy in various sectors, such as power utilities, industrial systems, and smart buildings. These systems support real-time analysis of data, predictive analytics, and automatic adjustments to improve energy efficiency, reduce expenses, and lower environmental footprints. This research introduces a new method of AI-based energy management through the creation of advanced mathematical aggregation operators under the theory of hesitant bipolar complex fuzzy sets (HBCFSs). The generalized HBCFS theory is a complete decision-making model that can efficiently deal with uncertainties, hesitancy, and bipolar information in a complex setting. To solve the intrinsic difficulties of energy management decision-making, we propose a series of new HBCF Hamacher power aggregation operators. These operators improve the precision and stability of multi-attribute decision-making (MADM) processes by using the Hamacher t-norm and power aggregation rules to represent intricate interactions among decision attributes. Further, a comparative study is conducted to highlight the strength and superiority of the proposed aggregation operators that significantly contribute to AI energy management systems. The results establish that the method developed significantly improves the accuracy and reliability of decisions, warranting application in energy distribution and usage optimization. |
|---|---|
| ISSN: | 2045-2322 |