Short‐term prediction of wind power based on temporal convolutional network and the informer model
Abstract In this study, a new short‐term wind power prediction model based on a temporal convolutional network (TCN) and the Informer model is proposed to solve the problem of low prediction accuracy caused by large wind speed fluctuations in short‐term prediction. First, an input feature selection...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2024-03-01
|
| Series: | IET Generation, Transmission & Distribution |
| Subjects: | |
| Online Access: | https://doi.org/10.1049/gtd2.13064 |
| _version_ | 1797278864613834752 |
|---|---|
| author | Shuohe Wang Linhua Chang Han Liu Yujian Chang Qiang Xue |
| author_facet | Shuohe Wang Linhua Chang Han Liu Yujian Chang Qiang Xue |
| author_sort | Shuohe Wang |
| collection | DOAJ |
| description | Abstract In this study, a new short‐term wind power prediction model based on a temporal convolutional network (TCN) and the Informer model is proposed to solve the problem of low prediction accuracy caused by large wind speed fluctuations in short‐term prediction. First, an input feature selection method based on the maximum information coefficient is proposed after considering the problem of information interference caused by excessively large input features. A dynamic time planning method is used to select the optimal input step of historical power. Then, the combined forecasting model composed of TCN and the Informer is constructed in accordance with the numerical weather forecast and historical power data. Lastly, the pinball loss function is used to expand the prediction model into a quantile regression model, measure the effect of volatility, quantify the volatility range of prediction, and finally, obtain a deterministic prediction result. The actual measured data of wind farms in the Bohai Sea area are selected for analysis and calculation. The results show that the prediction model proposed in this study achieves better accuracy in deterministic prediction and interval prediction than the traditional model. |
| first_indexed | 2024-03-07T16:15:16Z |
| format | Article |
| id | doaj.art-c764abc7fa3043cd8d6d012a6d7a6b7f |
| institution | Directory Open Access Journal |
| issn | 1751-8687 1751-8695 |
| language | English |
| last_indexed | 2024-03-07T16:15:16Z |
| publishDate | 2024-03-01 |
| publisher | Wiley |
| record_format | Article |
| series | IET Generation, Transmission & Distribution |
| spelling | doaj.art-c764abc7fa3043cd8d6d012a6d7a6b7f2024-03-04T11:27:49ZengWileyIET Generation, Transmission & Distribution1751-86871751-86952024-03-0118594195110.1049/gtd2.13064Short‐term prediction of wind power based on temporal convolutional network and the informer modelShuohe Wang0Linhua Chang1Han Liu2Yujian Chang3Qiang Xue4Hebei Provincial Collaborative Innovation Center of Transportation Power Grid Intelligent Integration Technology and Equipment Shijiazhuang Tiedao University Shijiazhuang ChinaHebei Provincial Collaborative Innovation Center of Transportation Power Grid Intelligent Integration Technology and Equipment Shijiazhuang Tiedao University Shijiazhuang ChinaTianjin Municipal Engineering Design and Research Institute Co. LTD Tianjin ChinaHebei Provincial Collaborative Innovation Center of Transportation Power Grid Intelligent Integration Technology and Equipment Shijiazhuang Tiedao University Shijiazhuang ChinaHebei Provincial Collaborative Innovation Center of Transportation Power Grid Intelligent Integration Technology and Equipment Shijiazhuang Tiedao University Shijiazhuang ChinaAbstract In this study, a new short‐term wind power prediction model based on a temporal convolutional network (TCN) and the Informer model is proposed to solve the problem of low prediction accuracy caused by large wind speed fluctuations in short‐term prediction. First, an input feature selection method based on the maximum information coefficient is proposed after considering the problem of information interference caused by excessively large input features. A dynamic time planning method is used to select the optimal input step of historical power. Then, the combined forecasting model composed of TCN and the Informer is constructed in accordance with the numerical weather forecast and historical power data. Lastly, the pinball loss function is used to expand the prediction model into a quantile regression model, measure the effect of volatility, quantify the volatility range of prediction, and finally, obtain a deterministic prediction result. The actual measured data of wind farms in the Bohai Sea area are selected for analysis and calculation. The results show that the prediction model proposed in this study achieves better accuracy in deterministic prediction and interval prediction than the traditional model.https://doi.org/10.1049/gtd2.13064forecasting theoryrenewable energy sourceswind power |
| spellingShingle | Shuohe Wang Linhua Chang Han Liu Yujian Chang Qiang Xue Short‐term prediction of wind power based on temporal convolutional network and the informer model IET Generation, Transmission & Distribution forecasting theory renewable energy sources wind power |
| title | Short‐term prediction of wind power based on temporal convolutional network and the informer model |
| title_full | Short‐term prediction of wind power based on temporal convolutional network and the informer model |
| title_fullStr | Short‐term prediction of wind power based on temporal convolutional network and the informer model |
| title_full_unstemmed | Short‐term prediction of wind power based on temporal convolutional network and the informer model |
| title_short | Short‐term prediction of wind power based on temporal convolutional network and the informer model |
| title_sort | short term prediction of wind power based on temporal convolutional network and the informer model |
| topic | forecasting theory renewable energy sources wind power |
| url | https://doi.org/10.1049/gtd2.13064 |
| work_keys_str_mv | AT shuohewang shorttermpredictionofwindpowerbasedontemporalconvolutionalnetworkandtheinformermodel AT linhuachang shorttermpredictionofwindpowerbasedontemporalconvolutionalnetworkandtheinformermodel AT hanliu shorttermpredictionofwindpowerbasedontemporalconvolutionalnetworkandtheinformermodel AT yujianchang shorttermpredictionofwindpowerbasedontemporalconvolutionalnetworkandtheinformermodel AT qiangxue shorttermpredictionofwindpowerbasedontemporalconvolutionalnetworkandtheinformermodel |