A Short-Term Wind Speed Forecasting Model Based on a Multi-Variable Long Short-Term Memory Network
Accurately forecasting wind speed on a short-term scale has become essential in the field of wind power energy. In this paper, a multi-variable long short-term memory network model (MV-LSTM) based on Pearson correlation coefficient feature selection is proposed to predict the short-term wind speed....
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-05-01
|
| Series: | Atmosphere |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-4433/12/5/651 |
| _version_ | 1797533436519383040 |
|---|---|
| author | Anqi Xie Hao Yang Jing Chen Li Sheng Qian Zhang |
| author_facet | Anqi Xie Hao Yang Jing Chen Li Sheng Qian Zhang |
| author_sort | Anqi Xie |
| collection | DOAJ |
| description | Accurately forecasting wind speed on a short-term scale has become essential in the field of wind power energy. In this paper, a multi-variable long short-term memory network model (MV-LSTM) based on Pearson correlation coefficient feature selection is proposed to predict the short-term wind speed. The proposed method utilizes multiple historical meteorological variables, such as wind speed, temperature, humidity, and air pressure, to predict the wind speed in the next hour. Hourly data collected from two ground observation stations in Yanqing and Zhaitang in Beijing were divided into training and test sets. The training sets were used to train the model, and the test sets were used to evaluate the model with the root-mean-square error (RMSE), mean absolute error (MAE), mean bias error (MBE), and mean absolute percentage error (MAPE) metrics. The proposed method is compared with two other forecasting methods (the autoregressive moving average model (ARMA) method and the single-variable long short-term memory network (LSTM) method, which inputs only historical wind speed data) based on the same dataset. The experimental results prove the feasibility of the MV-LSTM method for short-term wind speed forecasting and its superiority to the ARMA method and the single-variable LSTM method. |
| first_indexed | 2024-03-10T11:15:29Z |
| format | Article |
| id | doaj.art-bd70fe7d573649b095782a65a3008d14 |
| institution | Directory Open Access Journal |
| issn | 2073-4433 |
| language | English |
| last_indexed | 2024-03-10T11:15:29Z |
| publishDate | 2021-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Atmosphere |
| spelling | doaj.art-bd70fe7d573649b095782a65a3008d142023-11-21T20:30:00ZengMDPI AGAtmosphere2073-44332021-05-0112565110.3390/atmos12050651A Short-Term Wind Speed Forecasting Model Based on a Multi-Variable Long Short-Term Memory NetworkAnqi Xie0Hao Yang1Jing Chen2Li Sheng3Qian Zhang4School of Computer Science, Chengdu University of Information Technology, Chengdu 610225, ChinaSchool of Computer Science, Chengdu University of Information Technology, Chengdu 610225, ChinaNumerical Weather Prediction Center, CMA, Beijing 100081, ChinaNumerical Weather Prediction Center, CMA, Beijing 100081, ChinaSchool of Computer Science, University of Nottingham, Nottingham NG8 1BB, UKAccurately forecasting wind speed on a short-term scale has become essential in the field of wind power energy. In this paper, a multi-variable long short-term memory network model (MV-LSTM) based on Pearson correlation coefficient feature selection is proposed to predict the short-term wind speed. The proposed method utilizes multiple historical meteorological variables, such as wind speed, temperature, humidity, and air pressure, to predict the wind speed in the next hour. Hourly data collected from two ground observation stations in Yanqing and Zhaitang in Beijing were divided into training and test sets. The training sets were used to train the model, and the test sets were used to evaluate the model with the root-mean-square error (RMSE), mean absolute error (MAE), mean bias error (MBE), and mean absolute percentage error (MAPE) metrics. The proposed method is compared with two other forecasting methods (the autoregressive moving average model (ARMA) method and the single-variable long short-term memory network (LSTM) method, which inputs only historical wind speed data) based on the same dataset. The experimental results prove the feasibility of the MV-LSTM method for short-term wind speed forecasting and its superiority to the ARMA method and the single-variable LSTM method.https://www.mdpi.com/2073-4433/12/5/651wind speed predictionmulti-variableLSTMneural networks |
| spellingShingle | Anqi Xie Hao Yang Jing Chen Li Sheng Qian Zhang A Short-Term Wind Speed Forecasting Model Based on a Multi-Variable Long Short-Term Memory Network Atmosphere wind speed prediction multi-variable LSTM neural networks |
| title | A Short-Term Wind Speed Forecasting Model Based on a Multi-Variable Long Short-Term Memory Network |
| title_full | A Short-Term Wind Speed Forecasting Model Based on a Multi-Variable Long Short-Term Memory Network |
| title_fullStr | A Short-Term Wind Speed Forecasting Model Based on a Multi-Variable Long Short-Term Memory Network |
| title_full_unstemmed | A Short-Term Wind Speed Forecasting Model Based on a Multi-Variable Long Short-Term Memory Network |
| title_short | A Short-Term Wind Speed Forecasting Model Based on a Multi-Variable Long Short-Term Memory Network |
| title_sort | short term wind speed forecasting model based on a multi variable long short term memory network |
| topic | wind speed prediction multi-variable LSTM neural networks |
| url | https://www.mdpi.com/2073-4433/12/5/651 |
| work_keys_str_mv | AT anqixie ashorttermwindspeedforecastingmodelbasedonamultivariablelongshorttermmemorynetwork AT haoyang ashorttermwindspeedforecastingmodelbasedonamultivariablelongshorttermmemorynetwork AT jingchen ashorttermwindspeedforecastingmodelbasedonamultivariablelongshorttermmemorynetwork AT lisheng ashorttermwindspeedforecastingmodelbasedonamultivariablelongshorttermmemorynetwork AT qianzhang ashorttermwindspeedforecastingmodelbasedonamultivariablelongshorttermmemorynetwork AT anqixie shorttermwindspeedforecastingmodelbasedonamultivariablelongshorttermmemorynetwork AT haoyang shorttermwindspeedforecastingmodelbasedonamultivariablelongshorttermmemorynetwork AT jingchen shorttermwindspeedforecastingmodelbasedonamultivariablelongshorttermmemorynetwork AT lisheng shorttermwindspeedforecastingmodelbasedonamultivariablelongshorttermmemorynetwork AT qianzhang shorttermwindspeedforecastingmodelbasedonamultivariablelongshorttermmemorynetwork |