On the importance of the long-term seasonal component in day-ahead electricity price forecasting with NARX neural networks |
| |
| Institution: | 1. Department of Operations Research, Wrocław University of Science and Technology, Wrocław, Poland;2. Faculty of Pure and Applied Mathematics, Wrocław University of Science and Technology, Wrocław, Poland;1. School of Information Science and Engineering, Lanzhou University, Lanzhou, China;2. Network and communication Center, Lanzhou University, Lanzhou, China;1. Department of Operations Research, Wrocław University of Technology, Wrocław, Poland;2. CERGE-EI, Prague, Czech Republic;1. Delft Center for Systems and Control, Delft University of Technology, Mekelweg 2, Delft, The Netherlands;2. Algorithms, Modeling, and Optimization, VITO, Energyville, ThorPark, Genk, Belgium |
| |
| Abstract: | Daily and weekly seasonalities are always taken into account in day-ahead electricity price forecasting, but the long-term seasonal component has long been believed to add unnecessary complexity, and hence, most studies have ignored it. The recent introduction of the Seasonal Component AutoRegressive (SCAR) modeling framework has changed this viewpoint. However, this framework is based on linear models estimated using ordinary least squares. This paper shows that considering non-linear autoregressive (NARX) neural network-type models with the same inputs as the corresponding SCAR-type models can lead to yet better performances. While individual Seasonal Component Artificial Neural Network (SCANN) models are generally worse than the corresponding SCAR-type structures, we provide empirical evidence that committee machines of SCANN networks can outperform the latter significantly. |
| |
| Keywords: | Electricity spot price Forecasting Day-ahead market Long-term seasonal component NARX neural network Committee machine |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
