Machine Learning in Renewable Energy Systems

Munir, Muhammad Sohail, Shahid, Usama ORCID: https://orcid.org/0009-0005-6360-333X, Nasir, Usama, Hasan, Muhammad Zulkifl, Hussain, Muhammad Zunnurain, Fatima, Hoor and Yaqub, Muhammad Atif (2024) Machine Learning in Renewable Energy Systems. In: Proceedings of 2024 4th International Conference on Electrical, Computer, Communications and Mechatronics Engineering (ICECCME). IEEE, pp. 1-5. ISBN 9798350391183

Text 14804 Munir, Muhammad Sohail et al. (2024) Machine Learning in Renewable Energy Systems.pdf - Published Version Restricted to Repository staff only Available under License All Rights Reserved. Download (704kB)

Abstract

From solar and wind power to hydropower and biomass, smart grids, the catalytic industry, and power storage and distribution, this paper covers the gamut of ML's present-day uses. Among the many domains covered by machine learning are classification issues and the methods used to solve them. Classification schemes have recently attracted a lot of interest as a tool for improving the deployment, administration, and optimization of Renewable Energy Systems. The integration of new data sources (such as innovative sensors) and improved algorithms for creating trustworthy data will improve the data flow between ML and systems. The growth of other important areas of data science, such big data analytics, will determine the significance of unsupervised and reinforcement learning in the energy industry. The development of sustainable uses of ML in non-industrial applications for energy management will be aided by massive implementations, specialized algorithms, and new technologies like 5G. This work aims to survey the state-of-The-Art classification algorithms for Renewable Energy situations, including both traditional and cutting-edge methods. Wind speed/power prediction, fault diagnostics in Renewable Energy Systems, power quality disturbance categorization, and other applications in alternative Renewable Energy Systems are some of the particular Renewable Energy topics covered in the paper's extensive literature analysis and discussion. Researchers and practitioners in the area may benefit from the paper's description of categorization algorithms and metrics used to Renewable Energy situations.

Item Type:	Book Section
Additional Information:	4-6 November, 2024 Male, Maldives 4th International Conference on Electrical, Computer, Communications and Mechatronics Engineering (ICECCME)
Uncontrolled Keywords:	Machine learning; Renewable Energy Systems; Classification Algorithms; Data Science
Subjects:	Q Science > QA Mathematics > QA76 Computer software > QA76.9 Other topics > QA76.9.A43 Algorithms T Technology > TD Environmental technology. Sanitary engineering
Divisions:	Schools and Research Institutes > School of Business, Computing and Social Sciences
Depositing User:	Kamila Niekoraniec
Date Deposited:	27 Feb 2025 11:57
Last Modified:	12 Mar 2025 11:31
URI:	https://eprints.glos.ac.uk/id/eprint/14804

University Staff: Request a correction | Repository Editors: Update this record