High Precision LSTM Model for Short-Time Load Forecasting in Power Systems
The paper presents the application of recurrent LSTM neural networks for short-time load forecasting in the Polish Power System (PPS) and a small region of a power system in Central Poland. The objective of the present work was to develop an efficient and accurate method of forecasting the 24-h patt...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-05-01
|
| Series: | Energies |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1996-1073/14/11/2983 |
| _version_ | 1797533185731461120 |
|---|---|
| author | Tomasz Ciechulski Stanisław Osowski |
| author_facet | Tomasz Ciechulski Stanisław Osowski |
| author_sort | Tomasz Ciechulski |
| collection | DOAJ |
| description | The paper presents the application of recurrent LSTM neural networks for short-time load forecasting in the Polish Power System (PPS) and a small region of a power system in Central Poland. The objective of the present work was to develop an efficient and accurate method of forecasting the 24-h pattern of power load with a 1-h and 24-h horizon. LSTM showed effectiveness in predicting the irregular trends in time series. The final forecast is estimated using an ensemble consisted of five independent predictions. Numerical experiments proved the superiority of the ensemble above single predictor resulting in a reduction of the MAPE the RMSE error by more than 6% in both forecasting tasks. |
| first_indexed | 2024-03-10T11:10:56Z |
| format | Article |
| id | doaj.art-106ba0e1fa3c480899647f617614be94 |
| institution | Directory Open Access Journal |
| issn | 1996-1073 |
| language | English |
| last_indexed | 2024-03-10T11:10:56Z |
| publishDate | 2021-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Energies |
| spelling | doaj.art-106ba0e1fa3c480899647f617614be942023-11-21T20:44:46ZengMDPI AGEnergies1996-10732021-05-011411298310.3390/en14112983High Precision LSTM Model for Short-Time Load Forecasting in Power SystemsTomasz Ciechulski0Stanisław Osowski1Institute of Electronic Systems, Faculty of Electronics, Military University of Technology, ul. gen. Sylwestra Kaliskiego 2, 00-908 Warsaw, PolandInstitute of Electronic Systems, Faculty of Electronics, Military University of Technology, ul. gen. Sylwestra Kaliskiego 2, 00-908 Warsaw, PolandThe paper presents the application of recurrent LSTM neural networks for short-time load forecasting in the Polish Power System (PPS) and a small region of a power system in Central Poland. The objective of the present work was to develop an efficient and accurate method of forecasting the 24-h pattern of power load with a 1-h and 24-h horizon. LSTM showed effectiveness in predicting the irregular trends in time series. The final forecast is estimated using an ensemble consisted of five independent predictions. Numerical experiments proved the superiority of the ensemble above single predictor resulting in a reduction of the MAPE the RMSE error by more than 6% in both forecasting tasks.https://www.mdpi.com/1996-1073/14/11/2983recurrent LSTM networkload forecastingprediction systemspower systemsdemand-side management |
| spellingShingle | Tomasz Ciechulski Stanisław Osowski High Precision LSTM Model for Short-Time Load Forecasting in Power Systems Energies recurrent LSTM network load forecasting prediction systems power systems demand-side management |
| title | High Precision LSTM Model for Short-Time Load Forecasting in Power Systems |
| title_full | High Precision LSTM Model for Short-Time Load Forecasting in Power Systems |
| title_fullStr | High Precision LSTM Model for Short-Time Load Forecasting in Power Systems |
| title_full_unstemmed | High Precision LSTM Model for Short-Time Load Forecasting in Power Systems |
| title_short | High Precision LSTM Model for Short-Time Load Forecasting in Power Systems |
| title_sort | high precision lstm model for short time load forecasting in power systems |
| topic | recurrent LSTM network load forecasting prediction systems power systems demand-side management |
| url | https://www.mdpi.com/1996-1073/14/11/2983 |
| work_keys_str_mv | AT tomaszciechulski highprecisionlstmmodelforshorttimeloadforecastinginpowersystems AT stanisławosowski highprecisionlstmmodelforshorttimeloadforecastinginpowersystems |