Global Solar Irradiation Modelling and Prediction Using Machine Learning Models for Their Potential Use in Renewable Energy Applications
Global solar irradiation is an important variable that can be used to determine the suitability of an area to install solar systems; nevertheless, due to the limitations of requiring measurement stations around the entire world, it can be correlated with different meteorological parameters. To confr...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-12-01
|
| Series: | Mathematics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-7390/10/24/4746 |
| _version_ | 1797456486783254528 |
|---|---|
| author | David Puga-Gil Gonzalo Astray Enrique Barreiro Juan F. Gálvez Juan Carlos Mejuto |
| author_facet | David Puga-Gil Gonzalo Astray Enrique Barreiro Juan F. Gálvez Juan Carlos Mejuto |
| author_sort | David Puga-Gil |
| collection | DOAJ |
| description | Global solar irradiation is an important variable that can be used to determine the suitability of an area to install solar systems; nevertheless, due to the limitations of requiring measurement stations around the entire world, it can be correlated with different meteorological parameters. To confront this issue, different locations in Rias Baixas (Autonomous Community of Galicia, Spain) and combinations of parameters (month and average temperature, among others) were used to develop various machine learning models (random forest -RF-, support vector machine -SVM- and artificial neural network -ANN-). These three approaches were used to model and predict (one month ahead) monthly global solar irradiation using the data from six measurement stations. Afterwards, these models were applied to seven different measurement stations to check if the knowledge acquired could be extrapolated to other locations. In general, the ANN models offered the best results for the development and testing phases of the model, as well as for the phase of knowledge extrapolation to other locations. In this sense, the selected ANNs obtained a mean absolute percentage error (MAPE) value between 3.9 and 13.8% for the model development and an overall MAPE between 4.1 and 12.5% for the other seven locations. ANNs can be a capable tool for modelling and predicting monthly global solar irradiation in areas where data are available and for extrapolating this knowledge to nearby areas. |
| first_indexed | 2024-03-09T16:08:32Z |
| format | Article |
| id | doaj.art-e067b86a2bfa41a6a605368f771129f6 |
| institution | Directory Open Access Journal |
| issn | 2227-7390 |
| language | English |
| last_indexed | 2024-03-09T16:08:32Z |
| publishDate | 2022-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Mathematics |
| spelling | doaj.art-e067b86a2bfa41a6a605368f771129f62023-11-24T16:29:04ZengMDPI AGMathematics2227-73902022-12-011024474610.3390/math10244746Global Solar Irradiation Modelling and Prediction Using Machine Learning Models for Their Potential Use in Renewable Energy ApplicationsDavid Puga-Gil0Gonzalo Astray1Enrique Barreiro2Juan F. Gálvez3Juan Carlos Mejuto4Universidade de Vigo, Departamento de Química Física, Facultade de Ciencias, 32004 Ourense, EspañaUniversidade de Vigo, Departamento de Química Física, Facultade de Ciencias, 32004 Ourense, EspañaUniversidade de Vigo, Departamento de Informática, Escola Superior de Enxeñaría Informática, 32004 Ourense, EspañaUniversidade de Vigo, Departamento de Informática, Escola Superior de Enxeñaría Informática, 32004 Ourense, EspañaUniversidade de Vigo, Departamento de Química Física, Facultade de Ciencias, 32004 Ourense, EspañaGlobal solar irradiation is an important variable that can be used to determine the suitability of an area to install solar systems; nevertheless, due to the limitations of requiring measurement stations around the entire world, it can be correlated with different meteorological parameters. To confront this issue, different locations in Rias Baixas (Autonomous Community of Galicia, Spain) and combinations of parameters (month and average temperature, among others) were used to develop various machine learning models (random forest -RF-, support vector machine -SVM- and artificial neural network -ANN-). These three approaches were used to model and predict (one month ahead) monthly global solar irradiation using the data from six measurement stations. Afterwards, these models were applied to seven different measurement stations to check if the knowledge acquired could be extrapolated to other locations. In general, the ANN models offered the best results for the development and testing phases of the model, as well as for the phase of knowledge extrapolation to other locations. In this sense, the selected ANNs obtained a mean absolute percentage error (MAPE) value between 3.9 and 13.8% for the model development and an overall MAPE between 4.1 and 12.5% for the other seven locations. ANNs can be a capable tool for modelling and predicting monthly global solar irradiation in areas where data are available and for extrapolating this knowledge to nearby areas.https://www.mdpi.com/2227-7390/10/24/4746machine learningrandom forestsupport vector machineartificial neural networkglobal solar irradiationmodelling |
| spellingShingle | David Puga-Gil Gonzalo Astray Enrique Barreiro Juan F. Gálvez Juan Carlos Mejuto Global Solar Irradiation Modelling and Prediction Using Machine Learning Models for Their Potential Use in Renewable Energy Applications Mathematics machine learning random forest support vector machine artificial neural network global solar irradiation modelling |
| title | Global Solar Irradiation Modelling and Prediction Using Machine Learning Models for Their Potential Use in Renewable Energy Applications |
| title_full | Global Solar Irradiation Modelling and Prediction Using Machine Learning Models for Their Potential Use in Renewable Energy Applications |
| title_fullStr | Global Solar Irradiation Modelling and Prediction Using Machine Learning Models for Their Potential Use in Renewable Energy Applications |
| title_full_unstemmed | Global Solar Irradiation Modelling and Prediction Using Machine Learning Models for Their Potential Use in Renewable Energy Applications |
| title_short | Global Solar Irradiation Modelling and Prediction Using Machine Learning Models for Their Potential Use in Renewable Energy Applications |
| title_sort | global solar irradiation modelling and prediction using machine learning models for their potential use in renewable energy applications |
| topic | machine learning random forest support vector machine artificial neural network global solar irradiation modelling |
| url | https://www.mdpi.com/2227-7390/10/24/4746 |
| work_keys_str_mv | AT davidpugagil globalsolarirradiationmodellingandpredictionusingmachinelearningmodelsfortheirpotentialuseinrenewableenergyapplications AT gonzaloastray globalsolarirradiationmodellingandpredictionusingmachinelearningmodelsfortheirpotentialuseinrenewableenergyapplications AT enriquebarreiro globalsolarirradiationmodellingandpredictionusingmachinelearningmodelsfortheirpotentialuseinrenewableenergyapplications AT juanfgalvez globalsolarirradiationmodellingandpredictionusingmachinelearningmodelsfortheirpotentialuseinrenewableenergyapplications AT juancarlosmejuto globalsolarirradiationmodellingandpredictionusingmachinelearningmodelsfortheirpotentialuseinrenewableenergyapplications |