Short-term forecasting for solar irradiation based on the multi-layer neural network with the Levenberg-Marquardt algorithm and meteorological data: application to the Gandon site in Senegal
| Autor: | Oumar Ibn Khatab Cisse, Willy Magloire Nkounga, Mamadou Bop, Alexandre Sioutas, Mamadou Ndiaye, Mouhamadou Falilou Ndiaye |
|---|---|
| Rok vydání: | 2018 |
| Předmět: |
Normalized root mean square error
Mean squared error Meteorology Artificial neural network business.industry 020209 energy 02 engineering and technology Data application Term (time) Levenberg–Marquardt algorithm Software 0202 electrical engineering electronic engineering information engineering business Multi layer Mathematics |
| Zdroj: | 2018 7th International Conference on Renewable Energy Research and Applications (ICRERA). |
| DOI: | 10.1109/icrera.2018.8566850 |
| Popis: | This paper proposes a short-term forecast of the solar irradiation on the Gandon site in Senegal, based on the multi-layer artificial neural networks, with the Levenberg-Marquardt algorithm. The meteorological data are used as input variables. Due to the random nature of the meteorological variables, this forecast is necessary in order to plan the energy resources on the short-term. The forecast horizon is fixed at ten minutes. A data analysis with the WEKA (Waikato Environment for Knowledge Analysis) software permitted to select three input parameters (maximum temperature, mean radiation and time) among the nine measured and to determine four hidden layers. A comparative study is realized between the measured solar radiation on the site and the forecast results. The forecasted and measured data are correlated at 99% with a root mean square error (RMSE) of 0.0362, a time-statistical error of 9.25 and a normalized root mean square error (nRMSE) of 19.37%. These results show the efficiency of this model and the relevance of the chosen approach. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|