Solar Radiation Prediction on Photovoltaic Systems Using Machine Learning Techniques
Estimation of solar radiation is essential to help decision-makers in the planning of isolated solar energy farms or connected to electricity distribution networks to take advantage of renewable energy sources, reduce the impact produced by climate change, and increase coverage rates in electricity...
| Main Authors: | , , , |
|---|---|
| Format: | Online |
| Language: | spa |
| Published: |
Universidad Pedagógica y Tecnológica de Colombia
2020
|
| Subjects: | |
| Online Access: | https://revistas.uptc.edu.co/index.php/ingenieria/article/view/11751 |
| _version_ | 1801706089057615872 |
|---|---|
| author | Ordoñez-Palacios, Luis Eduardo León-Vargas, Daniel Andrés Bucheli-Guerrero, Víctor Andrés Ordoñez-Eraso, Hugo Armando |
| author_facet | Ordoñez-Palacios, Luis Eduardo León-Vargas, Daniel Andrés Bucheli-Guerrero, Víctor Andrés Ordoñez-Eraso, Hugo Armando |
| author_sort | Ordoñez-Palacios, Luis Eduardo |
| collection | OJS |
| description | Estimation of solar radiation is essential to help decision-makers in the planning of isolated solar energy farms or connected to electricity distribution networks to take advantage of renewable energy sources, reduce the impact produced by climate change, and increase coverage rates in electricity service. The number of existing measurement stations is insufficient to cover the entire geography of a region, and many of them are not capturing solar radiation data. Therefore, it is important to use mathematical, statistical, and artificial intelligence models, which allow predicting solar radiation from meteorological data available. In this work, datasets taken from measurement stations located in the cities of Cali and Villavicencio were used, in addition to a dataset generated by the World Weather Online API for the town of Mocoa, to carry out solar radiation estimations using different machine learning techniques for regression and classification to evaluate their performance. Although in most related works researchers used deep learning to predict solar radiation, this work showed that, while artificial neural networks are the most widely used technique, other machine learning algorithms such as Random Forest, Vector Support Machines and AdaBoost, also provide estimates with sufficient precision to be used in this field of study. |
| format | Online |
| id | oai:oai.revistas.uptc.edu.co:article-11751 |
| institution | Revista Facultad de Ingeniería |
| language | spa |
| publishDate | 2020 |
| publisher | Universidad Pedagógica y Tecnológica de Colombia |
| record_format | ojs |
| spelling | oai:oai.revistas.uptc.edu.co:article-117512021-07-13T02:23:22Z Solar Radiation Prediction on Photovoltaic Systems Using Machine Learning Techniques Predicción de radiación solar en sistemas fotovoltaicos utilizando técnicas de aprendizaje automático Ordoñez-Palacios, Luis Eduardo León-Vargas, Daniel Andrés Bucheli-Guerrero, Víctor Andrés Ordoñez-Eraso, Hugo Armando deep learning machine learning photovoltaic systems prediction model solar radiation supervised learning aprendizaje automático aprendizaje profundo aprendizaje supervisado modelo de predicción radiación solar sistemas fotovoltaicos Estimation of solar radiation is essential to help decision-makers in the planning of isolated solar energy farms or connected to electricity distribution networks to take advantage of renewable energy sources, reduce the impact produced by climate change, and increase coverage rates in electricity service. The number of existing measurement stations is insufficient to cover the entire geography of a region, and many of them are not capturing solar radiation data. Therefore, it is important to use mathematical, statistical, and artificial intelligence models, which allow predicting solar radiation from meteorological data available. In this work, datasets taken from measurement stations located in the cities of Cali and Villavicencio were used, in addition to a dataset generated by the World Weather Online API for the town of Mocoa, to carry out solar radiation estimations using different machine learning techniques for regression and classification to evaluate their performance. Although in most related works researchers used deep learning to predict solar radiation, this work showed that, while artificial neural networks are the most widely used technique, other machine learning algorithms such as Random Forest, Vector Support Machines and AdaBoost, also provide estimates with sufficient precision to be used in this field of study. La estimación de la radiación solar es fundamental para quienes participan en la planificación de granjas de energía solar, ya sean aisladas o conectadas a las redes de distribución eléctrica. Esto para el aprovechamiento de las fuentes de energía renovables, reducir el impacto producido por el cambio climático, e incrementar los índices de cobertura en el servicio eléctrico. De igual manera, el número de estaciones de medición existentes es insuficiente para cubrir toda la geografía de una región, y muchas de ellas no están capturando datos de radiación solar. Por consiguiente, es importante hacer uso de modelos matemáticos, estadísticos y de inteligencia artificial que permitan predecir la radiación solar a partir de datos meteorológicos disponibles. En este trabajo se utilizaron conjuntos de datos tomados de estaciones de medición ubicadas en las ciudades de Cali y Villavicencio, además de un conjunto de datos generado por la API World Weather Online para la ciudad de Mocoa. La razón fue realizar estimaciones de radiación solar utilizando distintas técnicas de aprendizaje automático para regresión y clasificación; el principal objetivo fue evaluar su desempeño. Aunque en la mayoría de los trabajos relacionados los investigadores utilizaron el aprendizaje profundo para la predicción de la radiación solar, este estudio demostró que, si bien las redes neuronales artificiales son la técnica más utilizada, otros algoritmos de aprendizaje automático como Random Forest, Máquinas de Soporte Vectorial y AdaBoost también proporcionan estimaciones con suficiente precisión para ser utilizados en este campo de estudio. Universidad Pedagógica y Tecnológica de Colombia 2020-09-18 info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion application/pdf application/xml https://revistas.uptc.edu.co/index.php/ingenieria/article/view/11751 10.19053/01211129.v29.n54.2020.11751 Revista Facultad de Ingeniería; Vol. 29 No. 54 (2020): Continuos Publication; e11751 Revista Facultad de Ingeniería; Vol. 29 Núm. 54 (2020): Publicación Continua; e11751 2357-5328 0121-1129 spa https://revistas.uptc.edu.co/index.php/ingenieria/article/view/11751/9617 https://revistas.uptc.edu.co/index.php/ingenieria/article/view/11751/10008 Copyright (c) 2020 Luis Eduardo Ordoñez-Palacios, Daniel Andrés León-Vargas, M.Sc., Víctor Andrés Bucheli-Guerrero, Ph. D., Hugo Armando Ordoñez-Eraso, Ph. D. |
| spellingShingle | deep learning machine learning photovoltaic systems prediction model solar radiation supervised learning aprendizaje automático aprendizaje profundo aprendizaje supervisado modelo de predicción radiación solar sistemas fotovoltaicos Ordoñez-Palacios, Luis Eduardo León-Vargas, Daniel Andrés Bucheli-Guerrero, Víctor Andrés Ordoñez-Eraso, Hugo Armando Solar Radiation Prediction on Photovoltaic Systems Using Machine Learning Techniques |
| title | Solar Radiation Prediction on Photovoltaic Systems Using Machine Learning Techniques |
| title_alt | Predicción de radiación solar en sistemas fotovoltaicos utilizando técnicas de aprendizaje automático |
| title_full | Solar Radiation Prediction on Photovoltaic Systems Using Machine Learning Techniques |
| title_fullStr | Solar Radiation Prediction on Photovoltaic Systems Using Machine Learning Techniques |
| title_full_unstemmed | Solar Radiation Prediction on Photovoltaic Systems Using Machine Learning Techniques |
| title_short | Solar Radiation Prediction on Photovoltaic Systems Using Machine Learning Techniques |
| title_sort | solar radiation prediction on photovoltaic systems using machine learning techniques |
| topic | deep learning machine learning photovoltaic systems prediction model solar radiation supervised learning aprendizaje automático aprendizaje profundo aprendizaje supervisado modelo de predicción radiación solar sistemas fotovoltaicos |
| topic_facet | deep learning machine learning photovoltaic systems prediction model solar radiation supervised learning aprendizaje automático aprendizaje profundo aprendizaje supervisado modelo de predicción radiación solar sistemas fotovoltaicos |
| url | https://revistas.uptc.edu.co/index.php/ingenieria/article/view/11751 |
| work_keys_str_mv | AT ordonezpalaciosluiseduardo solarradiationpredictiononphotovoltaicsystemsusingmachinelearningtechniques AT leonvargasdanielandres solarradiationpredictiononphotovoltaicsystemsusingmachinelearningtechniques AT bucheliguerrerovictorandres solarradiationpredictiononphotovoltaicsystemsusingmachinelearningtechniques AT ordonezerasohugoarmando solarradiationpredictiononphotovoltaicsystemsusingmachinelearningtechniques AT ordonezpalaciosluiseduardo prediccionderadiacionsolarensistemasfotovoltaicosutilizandotecnicasdeaprendizajeautomatico AT leonvargasdanielandres prediccionderadiacionsolarensistemasfotovoltaicosutilizandotecnicasdeaprendizajeautomatico AT bucheliguerrerovictorandres prediccionderadiacionsolarensistemasfotovoltaicosutilizandotecnicasdeaprendizajeautomatico AT ordonezerasohugoarmando prediccionderadiacionsolarensistemasfotovoltaicosutilizandotecnicasdeaprendizajeautomatico |
