|
Electricity load forecasting using a deep neural network |
|---|---|
| รหัสดีโอไอ | |
| Creator | 1. Pyae Pyae Phyo 2. Chawalit Jeenanunta |
| Title | Electricity load forecasting using a deep neural network |
| Publisher | Faculty of Engineering, Khon Kaen University |
| Publication Year | 2562 |
| Journal Title | Engineering and Applied Science Research |
| Journal Vol. | 46 |
| Journal No. | 1 |
| Page no. | 10-17 |
| Keyword | Deep neural network, Artificial neural network, Support vector machines, Forecasting, Short-term load forecasting |
| URL Website | https://www.tci-thaijo.org/index.php/easr/index |
| Website title | Engineering and Applied Science Research |
| ISSN | 2539-6161 |
| Abstract | Forecasting the daily load demand of an electric utility provider is a complex problem as it is nonlinear and influenced by external factors. Deep learning, machine learning and artificial intelligence techniques have been successfully employed in electric consumption load, financial market, and reliability predictions. In this paper, we propose the use of a deep neural network (DNN) for short-term load forecasting (STLF) to overcome nonlinearity problems and to achieve higher forecasting accuracy. Historical data was collected every 30 minutes for 24 hour periods from the Electricity Generating Authority of Thailand (EGAT). The proposed techniques were tested with cleaned data from 2012 to 2013, where holidays, bridging holidays, and outliers were replaced. The forecasting accuracy is indicated by the mean absolute percentage error (MAPE). In this paper, there are two different training datasets, everyday training dataset which is arranged by day sequentially and same day training dataset which is separated seven groups of day (for e.g., only Monday training is used to forecast Monday). The outcomes of a deep neural network (DNN) are compared with an artificial neural network (ANN) and support vector machines (SVM) with an everyday training dataset. The empirical results reveal that the proposed DNN model outperforms the ANN and SVM models. Moreover, the DNN model trained with same day training datasets provides better performance than a DNN trained with an everyday training dataset for weekends, bridging holidays, and Mondays. Additionally, the DNN using a same day training datasets provides higher accuracies for December and January. |
