Ultra‐short‐term multi‐step wind power forecasting based on CNN‐LSTM
Abstract The fluctuation and intermission of large‐scale wind power integration is a serious threat to the stability and security of the power system. Accurate prediction of wind power is of great significance to the safety of wind power grid connection. This study proposes a novel spatio‐temporal c...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2021-04-01
|
| Series: | IET Renewable Power Generation |
| Subjects: | |
| Online Access: | https://doi.org/10.1049/rpg2.12085 |
| _version_ | 1798031628334792704 |
|---|---|
| author | Qianyu Wu Fei Guan Chen Lv Yongzhang Huang |
| author_facet | Qianyu Wu Fei Guan Chen Lv Yongzhang Huang |
| author_sort | Qianyu Wu |
| collection | DOAJ |
| description | Abstract The fluctuation and intermission of large‐scale wind power integration is a serious threat to the stability and security of the power system. Accurate prediction of wind power is of great significance to the safety of wind power grid connection. This study proposes a novel spatio‐temporal correlation model (STCM) for ultra‐short‐term wind power prediction based on convolutional neural networks‐long short‐term memory (CNN‐LSTM). The original meteorological factors at multi‐historical time points of different sites throughout the target wind farm can be reconstructed into the input window of the model, and thus a new data reconstruction method is represented. CNN is used to extract the spatial correlation feature vectors of meteorological factors of different sites and the temporal correlation vectors of the meteorological features in ultra‐short term, which are reconstructed in time series and used as the input data of LSTM. Then, LSTM extracts the temporal feature relationship between the historical time points for multi‐step wind power forecasting. The STCM based on CNN‐LSTM proposed in this study is suitable for wind farms that can collect meteorological factors at different locations. Taking the measured meteorological factors and wind power dataset of a wind farm in China as an example, four evaluation metrics of the CNN‐LSTM model, CNN and LSTM individually used for multi‐step wind power prediction, are obtained. The results show that the proposed STCM based on CNN‐LSTM has better spatial and temporal characteristics extraction ability than the traditional structure model and can forecast the power of wind farm more accurately. |
| first_indexed | 2024-04-11T20:00:42Z |
| format | Article |
| id | doaj.art-c68a97b90d654fc6bea53f49fe82b063 |
| institution | Directory Open Access Journal |
| issn | 1752-1416 1752-1424 |
| language | English |
| last_indexed | 2024-04-11T20:00:42Z |
| publishDate | 2021-04-01 |
| publisher | Wiley |
| record_format | Article |
| series | IET Renewable Power Generation |
| spelling | doaj.art-c68a97b90d654fc6bea53f49fe82b0632022-12-22T04:05:39ZengWileyIET Renewable Power Generation1752-14161752-14242021-04-011551019102910.1049/rpg2.12085Ultra‐short‐term multi‐step wind power forecasting based on CNN‐LSTMQianyu Wu0Fei Guan1Chen Lv2Yongzhang Huang3State Key Laboratory of Alternate Electrical Power System with Renewable Energy Sources North China Electric Power University Beijing People's Republic of ChinaState Key Laboratory of Alternate Electrical Power System with Renewable Energy Sources North China Electric Power University Beijing People's Republic of ChinaChina Electric Power Research Institute Beijing ChinaState Key Laboratory of Alternate Electrical Power System with Renewable Energy Sources North China Electric Power University Beijing People's Republic of ChinaAbstract The fluctuation and intermission of large‐scale wind power integration is a serious threat to the stability and security of the power system. Accurate prediction of wind power is of great significance to the safety of wind power grid connection. This study proposes a novel spatio‐temporal correlation model (STCM) for ultra‐short‐term wind power prediction based on convolutional neural networks‐long short‐term memory (CNN‐LSTM). The original meteorological factors at multi‐historical time points of different sites throughout the target wind farm can be reconstructed into the input window of the model, and thus a new data reconstruction method is represented. CNN is used to extract the spatial correlation feature vectors of meteorological factors of different sites and the temporal correlation vectors of the meteorological features in ultra‐short term, which are reconstructed in time series and used as the input data of LSTM. Then, LSTM extracts the temporal feature relationship between the historical time points for multi‐step wind power forecasting. The STCM based on CNN‐LSTM proposed in this study is suitable for wind farms that can collect meteorological factors at different locations. Taking the measured meteorological factors and wind power dataset of a wind farm in China as an example, four evaluation metrics of the CNN‐LSTM model, CNN and LSTM individually used for multi‐step wind power prediction, are obtained. The results show that the proposed STCM based on CNN‐LSTM has better spatial and temporal characteristics extraction ability than the traditional structure model and can forecast the power of wind farm more accurately.https://doi.org/10.1049/rpg2.12085Power system controlPower system planning and layoutWind power plantsPower engineering computingTime seriesTime series |
| spellingShingle | Qianyu Wu Fei Guan Chen Lv Yongzhang Huang Ultra‐short‐term multi‐step wind power forecasting based on CNN‐LSTM IET Renewable Power Generation Power system control Power system planning and layout Wind power plants Power engineering computing Time series Time series |
| title | Ultra‐short‐term multi‐step wind power forecasting based on CNN‐LSTM |
| title_full | Ultra‐short‐term multi‐step wind power forecasting based on CNN‐LSTM |
| title_fullStr | Ultra‐short‐term multi‐step wind power forecasting based on CNN‐LSTM |
| title_full_unstemmed | Ultra‐short‐term multi‐step wind power forecasting based on CNN‐LSTM |
| title_short | Ultra‐short‐term multi‐step wind power forecasting based on CNN‐LSTM |
| title_sort | ultra short term multi step wind power forecasting based on cnn lstm |
| topic | Power system control Power system planning and layout Wind power plants Power engineering computing Time series Time series |
| url | https://doi.org/10.1049/rpg2.12085 |
| work_keys_str_mv | AT qianyuwu ultrashorttermmultistepwindpowerforecastingbasedoncnnlstm AT feiguan ultrashorttermmultistepwindpowerforecastingbasedoncnnlstm AT chenlv ultrashorttermmultistepwindpowerforecastingbasedoncnnlstm AT yongzhanghuang ultrashorttermmultistepwindpowerforecastingbasedoncnnlstm |