Data-Mining-based filtering to support Solar Forecasting Methodologies
This paper proposes an hybrid approach for short term solar intensity forecasting, which combines different forecasting methodologies with a clustering algorithm, which plays the role of data filter, in order to support the selection of the best data for training. A set of methodologies based on Art...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Ediciones Universidad de Salamanca
2017-11-01
|
| Series: | Advances in Distributed Computing and Artificial Intelligence Journal |
| Subjects: | |
| Online Access: | https://revistas.usal.es/index.php/2255-2863/article/view/17015 |
| _version_ | 1818370381999767552 |
|---|---|
| author | Tiago PINTO Luis MARQUES Tiago M SOUSA Isabel PRAÇA Zita VALE Samuel L ABREU |
| author_facet | Tiago PINTO Luis MARQUES Tiago M SOUSA Isabel PRAÇA Zita VALE Samuel L ABREU |
| author_sort | Tiago PINTO |
| collection | DOAJ |
| description | This paper proposes an hybrid approach for short term solar intensity forecasting, which combines different forecasting methodologies with a clustering algorithm, which plays the role of data filter, in order to support the selection of the best data for training. A set of methodologies based on Artificial Neural Networks (ANN) and Support Vector Machines (SVM), used for short term solar irradiance forecast, is implemented and compared in order to facilitate the selection of the most appropriate methods and respective parameters according to the available information and needs. Data from the Brazilian city of Florianópolis, in the state of Santa Catarina, has been used to illustrate the methods applicability and conclusions. The dataset comprises the years of 1990 to 1999 and includes four solar irradiance components as well as other meteorological variables, such as temperature, wind speed and humidity. Conclusions about the irradiance components, parameters and the proposed clustering mechanism are presented. The results are studied and analysed considering both efficiency and effectiveness of the results. The experimental findings show that the hybrid model, combining a SVM approach with a clustering mechanism, to filter the data used for training, achieved promising results, outperforming the approaches without clustering. |
| first_indexed | 2024-12-13T23:38:51Z |
| format | Article |
| id | doaj.art-7698c31bcc8f435f909bddc03066409e |
| institution | Directory Open Access Journal |
| issn | 2255-2863 |
| language | English |
| last_indexed | 2024-12-13T23:38:51Z |
| publishDate | 2017-11-01 |
| publisher | Ediciones Universidad de Salamanca |
| record_format | Article |
| series | Advances in Distributed Computing and Artificial Intelligence Journal |
| spelling | doaj.art-7698c31bcc8f435f909bddc03066409e2022-12-21T23:27:13ZengEdiciones Universidad de SalamancaAdvances in Distributed Computing and Artificial Intelligence Journal2255-28632017-11-01638510210.14201/ADCAIJ2017638510214900Data-Mining-based filtering to support Solar Forecasting MethodologiesTiago PINTO0Luis MARQUES1Tiago M SOUSA2Isabel PRAÇA3Zita VALE4Samuel L ABREU5BISITE - University of SalamancaGECAD - Polytechnic of PortoGECAD - Polytechnic of PortoGECAD - Polytechnic of PortoGECAD - Polytechnic of PortoGeneral – Alternative Energies Group - IFSC – Instituto Federal de Santa CatarinaThis paper proposes an hybrid approach for short term solar intensity forecasting, which combines different forecasting methodologies with a clustering algorithm, which plays the role of data filter, in order to support the selection of the best data for training. A set of methodologies based on Artificial Neural Networks (ANN) and Support Vector Machines (SVM), used for short term solar irradiance forecast, is implemented and compared in order to facilitate the selection of the most appropriate methods and respective parameters according to the available information and needs. Data from the Brazilian city of Florianópolis, in the state of Santa Catarina, has been used to illustrate the methods applicability and conclusions. The dataset comprises the years of 1990 to 1999 and includes four solar irradiance components as well as other meteorological variables, such as temperature, wind speed and humidity. Conclusions about the irradiance components, parameters and the proposed clustering mechanism are presented. The results are studied and analysed considering both efficiency and effectiveness of the results. The experimental findings show that the hybrid model, combining a SVM approach with a clustering mechanism, to filter the data used for training, achieved promising results, outperforming the approaches without clustering.https://revistas.usal.es/index.php/2255-2863/article/view/17015artificial neural networkclustering, data miningmachine learningsolar forecastingsupport vector machine |
| spellingShingle | Tiago PINTO Luis MARQUES Tiago M SOUSA Isabel PRAÇA Zita VALE Samuel L ABREU Data-Mining-based filtering to support Solar Forecasting Methodologies Advances in Distributed Computing and Artificial Intelligence Journal artificial neural network clustering, data mining machine learning solar forecasting support vector machine |
| title | Data-Mining-based filtering to support Solar Forecasting Methodologies |
| title_full | Data-Mining-based filtering to support Solar Forecasting Methodologies |
| title_fullStr | Data-Mining-based filtering to support Solar Forecasting Methodologies |
| title_full_unstemmed | Data-Mining-based filtering to support Solar Forecasting Methodologies |
| title_short | Data-Mining-based filtering to support Solar Forecasting Methodologies |
| title_sort | data mining based filtering to support solar forecasting methodologies |
| topic | artificial neural network clustering, data mining machine learning solar forecasting support vector machine |
| url | https://revistas.usal.es/index.php/2255-2863/article/view/17015 |
| work_keys_str_mv | AT tiagopinto dataminingbasedfilteringtosupportsolarforecastingmethodologies AT luismarques dataminingbasedfilteringtosupportsolarforecastingmethodologies AT tiagomsousa dataminingbasedfilteringtosupportsolarforecastingmethodologies AT isabelpraca dataminingbasedfilteringtosupportsolarforecastingmethodologies AT zitavale dataminingbasedfilteringtosupportsolarforecastingmethodologies AT samuellabreu dataminingbasedfilteringtosupportsolarforecastingmethodologies |