Predicción de la radiación solar utilizando redes neuronales para el dimensionamiento de plantas fotovoltaicas en la provincia de Pichincha.
The current research work is made, due to the increase in the renewable energies use for the electrical energy supplying, which allows to the take advantage the sun, as a solar energy inexhaustible source, so the project focuses on the solar radiation prediction for the photovoltaic plants sizing in...
Saved in:
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | bachelorThesis |
| Language: | spa |
| Published: |
2023
|
| Subjects: | |
| Online Access: | http://repositorio.utc.edu.ec/handle/27000/11418 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Add Tag | Summary: | The current research work is made, due to the increase in the renewable energies use for the electrical energy supplying, which allows to the take advantage the sun, as a solar energy inexhaustible source, so the project focuses on the solar radiation prediction for the photovoltaic plants sizing in the Pichincha province. For the effect, it is used a based approach on artificial neural networks, by considering three years solar radiation real data. Artificial neural networks are employed, due to their ability to learn from the real data behavior and characteristics. The methodology covers both descriptive and experimental approaches making programming and simulation tools use, by starting from a preprocessing process and data normalization to create training and validation sets. The prediction model implementation is carried by programming in free Python software, further, the got results are analyzed, through PVsyst and Homer Pro software use, validating the results, through the mean absolute error and by the matrix confusion and the graphics analysis. Getting as an answer, an annual energy generated 8594 MWh/year under the conditions taken in the current research work, thus demonstrating, which the solar radiation values prediction is viable for the photovoltaic plants sizing as a previous study for its implementation. |
|---|