| Título |
Neural networks for GEFCom2017 probabilistic load forecasting |
| Autores |
Dimoulkas I. , MAZIDI, PEYMAN, Herre L. |
| Publicación externa |
No |
| Medio |
Int. J. Forecast. |
| Alcance |
Article |
| Naturaleza |
Científica |
| Cuartil JCR |
1 |
| Cuartil SJR |
1 |
| Impacto JCR |
2.82500 |
| Impacto SJR |
1.75300 |
| Web |
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85057737557&doi=10.1016%2fj.ijforecast.2018.09.007&partnerID=40&md5=4b6e1bad467fc45ef1a551a95491886c |
| Fecha de publicacion |
01/01/2019 |
| ISI |
000490649500017 |
| Scopus Id |
2-s2.0-85057737557 |
| DOI |
10.1016/j.ijforecast.2018.09.007 |
| Abstract |
This report describes the forecasting model which was developed by team 4C for the global energy forecasting competition 2017 (GEFCom2017), with some modifications added afterwards to improve its accuracy. The model is based on neural networks. Temperature scenarios obtained from historical data are used as inputs to the neural networks in order to create load scenarios, and these load scenarios are then transformed into quantiles. By using a feature selection approach that is based on a stepwise regression technique, a neural network based model is developed for each zone. Furthermore, a dynamic choice of the temperature scenarios is suggested. The feature selection and dynamic choice of the temperature scenarios can improve the quantile scores considerably, resulting in very accurate forecasts among the top teams. © 2018 International Institute of Forecasters |
| Palabras clave |
Feature selection; GEFCom2017; Neural networks; Probabilistic load forecasting; Temperature scenarios |
| Miembros de la Universidad Loyola |
|
Gestionar cookies