Short‐term wind speed multistep combined forecasting model based on two‐stage decomposition and LSTM
Abstract In order to better extract and study the characteristics of the wind speed in time‐domain and frequency‐domain, so as to solve the time‐domain randomness and frequency‐domain complexity problems of the wind speed signal, a combined short‐term prediction model (WD‐VMD‐DLSTM‐AT), which is bas...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2021-09-01
|
| Series: | Wind Energy |
| Subjects: | |
| Online Access: | https://doi.org/10.1002/we.2613 |
| _version_ | 1831775843864543232 |
|---|---|
| author | Xuechao Liao Zhenxing Liu Wanxiong Deng |
| author_facet | Xuechao Liao Zhenxing Liu Wanxiong Deng |
| author_sort | Xuechao Liao |
| collection | DOAJ |
| description | Abstract In order to better extract and study the characteristics of the wind speed in time‐domain and frequency‐domain, so as to solve the time‐domain randomness and frequency‐domain complexity problems of the wind speed signal, a combined short‐term prediction model (WD‐VMD‐DLSTM‐AT), which is based on two‐stage decomposition (WD + VMD), double long‐short‐term memory network (DLSTM) and attention mechanism (AT), is proposed; on this basis, a multi‐input multiple output (MIMO) codec model based on attention mechanism (MMED‐AT) is proposed for multiple short‐term wind speed step forecast. Through experimental comparison and analysis, the proposed combined forecasting model has the smallest statistical error and the best prediction accuracy; the MMED‐AT models based on the combined model can obviously eliminate the cumulative error of recursive multistep prediction and further improve the stability of multistep prediction. |
| first_indexed | 2024-12-22T09:23:31Z |
| format | Article |
| id | doaj.art-cd38f6e54df94c3fb4edc03563799591 |
| institution | Directory Open Access Journal |
| issn | 1095-4244 1099-1824 |
| language | English |
| last_indexed | 2024-12-22T09:23:31Z |
| publishDate | 2021-09-01 |
| publisher | Wiley |
| record_format | Article |
| series | Wind Energy |
| spelling | doaj.art-cd38f6e54df94c3fb4edc035637995912022-12-21T18:31:09ZengWileyWind Energy1095-42441099-18242021-09-01249991101210.1002/we.2613Short‐term wind speed multistep combined forecasting model based on two‐stage decomposition and LSTMXuechao Liao0Zhenxing Liu1Wanxiong Deng2School of Computer Science and Technology Wuhan University of Science and Technology Wuhan ChinaSchool of Information Science and Engineering Wuhan University of Science and Technology Wuhan ChinaSchool of Computer Science and Technology Wuhan University of Science and Technology Wuhan ChinaAbstract In order to better extract and study the characteristics of the wind speed in time‐domain and frequency‐domain, so as to solve the time‐domain randomness and frequency‐domain complexity problems of the wind speed signal, a combined short‐term prediction model (WD‐VMD‐DLSTM‐AT), which is based on two‐stage decomposition (WD + VMD), double long‐short‐term memory network (DLSTM) and attention mechanism (AT), is proposed; on this basis, a multi‐input multiple output (MIMO) codec model based on attention mechanism (MMED‐AT) is proposed for multiple short‐term wind speed step forecast. Through experimental comparison and analysis, the proposed combined forecasting model has the smallest statistical error and the best prediction accuracy; the MMED‐AT models based on the combined model can obviously eliminate the cumulative error of recursive multistep prediction and further improve the stability of multistep prediction.https://doi.org/10.1002/we.2613attention mechanismLSTM (long‐short term memory)short‐term wind speed forecastVMD (variational mode decomposition)wavelet decomposition and reconstruction |
| spellingShingle | Xuechao Liao Zhenxing Liu Wanxiong Deng Short‐term wind speed multistep combined forecasting model based on two‐stage decomposition and LSTM Wind Energy attention mechanism LSTM (long‐short term memory) short‐term wind speed forecast VMD (variational mode decomposition) wavelet decomposition and reconstruction |
| title | Short‐term wind speed multistep combined forecasting model based on two‐stage decomposition and LSTM |
| title_full | Short‐term wind speed multistep combined forecasting model based on two‐stage decomposition and LSTM |
| title_fullStr | Short‐term wind speed multistep combined forecasting model based on two‐stage decomposition and LSTM |
| title_full_unstemmed | Short‐term wind speed multistep combined forecasting model based on two‐stage decomposition and LSTM |
| title_short | Short‐term wind speed multistep combined forecasting model based on two‐stage decomposition and LSTM |
| title_sort | short term wind speed multistep combined forecasting model based on two stage decomposition and lstm |
| topic | attention mechanism LSTM (long‐short term memory) short‐term wind speed forecast VMD (variational mode decomposition) wavelet decomposition and reconstruction |
| url | https://doi.org/10.1002/we.2613 |
| work_keys_str_mv | AT xuechaoliao shorttermwindspeedmultistepcombinedforecastingmodelbasedontwostagedecompositionandlstm AT zhenxingliu shorttermwindspeedmultistepcombinedforecastingmodelbasedontwostagedecompositionandlstm AT wanxiongdeng shorttermwindspeedmultistepcombinedforecastingmodelbasedontwostagedecompositionandlstm |