| _version_ | 1866901185555857408 |
|---|---|
| author | Muhammad Atiq ur rehman Muhammad Sajjad Khan Sergio Rivera* |
| author_facet | Muhammad Atiq ur rehman Muhammad Sajjad Khan Sergio Rivera* |
| contents | <p><strong><span>Abstract:</span></strong><span> </span><span>Application of machine learning techniques in power systems has a wide scope in research work due to their benefits in classification and regression characteristics in load balancing, fault tolerance, task processing time, and statistical nature of renewable energy resources. We have analyzed the characteristics of networked microgrids in context of their connectivity with main grid. In this paper, machine learning techniques are discussed which are applicable to distribution control, energy trading, optimization and power restoration in case of networked microgrid schemes. Paper focuses on recent progress of machine learning techniques in several aspects of <span>networked microgrids such as control and optimization process. We have used machine learning techniques for networked microgrids applications and their review. The main problem and challenge are to achieve renewable energy resources benefits and space for high number of microgrids penetration to design a comprehensive networked microgrids management system. This comprehensive networked microgrids management system is the robust decision center by using intelligent machine learning techniques. Machine learning techniques mapped the human learning process of improving accuracy of solution over time with data and algorithms. Machine learning algorithms used the data sets, training the computers for output values within the required limits. With the support of machine learning techniques, the existing information and experience lead to take right decision for controlling and management of networked microgrids. In addition, this review paper demonstrates the development of </span>machine learning techniques based on distributed and centralized control framework for networked microgrids</span><span>. </span></p> <p> </p> |
| format | Recurso digital |
| id | zenodo_https___doi_org_10_5281_zenodo_15761049 |
| institution | Zenodo |
| language | eng |
| publishDate | 2025 |
| publisher | Zenodo |
| record_format | zenodo |
| spellingShingle | A Review on Machine Learning Techniques in Networked Microgrids Applications Muhammad Atiq ur rehman Muhammad Sajjad Khan Sergio Rivera* Load Balancing, Networked Microgrids, Machine Learning, Data Science, Distributed and Centralized Control. <p><strong><span>Abstract:</span></strong><span> </span><span>Application of machine learning techniques in power systems has a wide scope in research work due to their benefits in classification and regression characteristics in load balancing, fault tolerance, task processing time, and statistical nature of renewable energy resources. We have analyzed the characteristics of networked microgrids in context of their connectivity with main grid. In this paper, machine learning techniques are discussed which are applicable to distribution control, energy trading, optimization and power restoration in case of networked microgrid schemes. Paper focuses on recent progress of machine learning techniques in several aspects of <span>networked microgrids such as control and optimization process. We have used machine learning techniques for networked microgrids applications and their review. The main problem and challenge are to achieve renewable energy resources benefits and space for high number of microgrids penetration to design a comprehensive networked microgrids management system. This comprehensive networked microgrids management system is the robust decision center by using intelligent machine learning techniques. Machine learning techniques mapped the human learning process of improving accuracy of solution over time with data and algorithms. Machine learning algorithms used the data sets, training the computers for output values within the required limits. With the support of machine learning techniques, the existing information and experience lead to take right decision for controlling and management of networked microgrids. In addition, this review paper demonstrates the development of </span>machine learning techniques based on distributed and centralized control framework for networked microgrids</span><span>. </span></p> <p> </p> |
| title | A Review on Machine Learning Techniques in Networked Microgrids Applications |
| topic | Load Balancing, Networked Microgrids, Machine Learning, Data Science, Distributed and Centralized Control. |
| url | https://doi.org/10.5281/zenodo.15761049 |