A Hybrid Intelligent Modeling approach for predicting the solar thermal panel energy production
![Thumbnail](/dspace/bitstream/handle/2183/36303/Arroyo_A_2024_A_hybrid_intelligent_modeling_approach_for_predicting_the_solar.pdf.jpg?sequence=5&isAllowed=y)
Ver/ abrir
Use este enlace para citar
http://hdl.handle.net/2183/36303
A non ser que se indique outra cousa, a licenza do ítem descríbese como CC BY Attribution 4.0 International http://creativecommons.org/licenses/by/4.0
Coleccións
- GI-CTC - Artigos [67]
Metadatos
Mostrar o rexistro completo do ítemTítulo
A Hybrid Intelligent Modeling approach for predicting the solar thermal panel energy productionData
2024-01-14Resumo
[Abstract] There is no doubt that the European Union is undergoing an ecological transition, with renewable energies accounting for an increasing share of energy consumption in the Member States. In Spain, solar energy is one of these rapidly expanding renewable sources. This study analyzes the solar energy production of a panel in the Spanish region of Galicia. It has been demonstrated that the solar energy produced by this panel can be predicted using a hybrid stepwise system. The missing value imputation is a key step in the process. This involves combining regression and clustering techniques on different subdivisions of the complete dataset, starting with a smaller and less complete dataset and performing appropriate imputations to create a larger and more complete collection. Finally, the dataset is divided into more relevant subsets for regression analysis to calculate the amount of solar energy generated. The imputing missing values using an Artificial Neural Network resulted in a more valid dataset for further processing than eliminating rows with corrupted or empty values. Also, properly applying clustering techniques gives better results than working on the whole dataset.
Palabras chave
Regression
Neural network
Solar energy
Renewable energy
Clustering
Neural network
Solar energy
Renewable energy
Clustering
Descrición
Funding for open access charge: Universidade da Coruña/CISUG.
Versión do editor
Dereitos
CC BY Attribution 4.0 International http://creativecommons.org/licenses/by/4.0
ISSN
1872-8286