Short-Term Power Prediction of Wind Turbine Applying Machine Learning and Digital Filter
As wind energy development increases, accurate wind energy forecasting helps to develop sensible power generation plans and ensure a balance between supply and demand. Machine-learning-based forecasting models possess exceptional predictive capabilities, and data manipulation prior to model training...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-01-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/13/3/1751 |
| _version_ | 1797625082114211840 |
|---|---|
| author | Shujun Liu Yaocong Zhang Xiaoze Du Tong Xu Jiangbo Wu |
| author_facet | Shujun Liu Yaocong Zhang Xiaoze Du Tong Xu Jiangbo Wu |
| author_sort | Shujun Liu |
| collection | DOAJ |
| description | As wind energy development increases, accurate wind energy forecasting helps to develop sensible power generation plans and ensure a balance between supply and demand. Machine-learning-based forecasting models possess exceptional predictive capabilities, and data manipulation prior to model training is also a key focus of this research. This study trained a deep Long Short-Term Memory (LSTM) neural network to learn the processing results of the Savitzky-Golay filter, which can avoid overfitting due to fluctuations and noise in measurements, improving the generalization performance. The optimum data frame length to match the second-order filter was determined by comparison. In a single-step prediction, the method reduced the root-mean-square error by 3.8% compared to the model trained directly with the measurements. The method also produced the smallest errors in all steps of the multi-step advance prediction. The proposed method ensures the accuracy of the forecasting and, on that basis, also improves the timeliness of the effective forecasts. |
| first_indexed | 2024-03-11T09:51:47Z |
| format | Article |
| id | doaj.art-24024d2090044f339669328be1465f69 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-11T09:51:47Z |
| publishDate | 2023-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-24024d2090044f339669328be1465f692023-11-16T16:09:54ZengMDPI AGApplied Sciences2076-34172023-01-01133175110.3390/app13031751Short-Term Power Prediction of Wind Turbine Applying Machine Learning and Digital FilterShujun Liu0Yaocong Zhang1Xiaoze Du2Tong Xu3Jiangbo Wu4School of Energy and Power Engineering, Lanzhou University of Technology, Lanzhou 730050, ChinaSchool of Energy and Power Engineering, Lanzhou University of Technology, Lanzhou 730050, ChinaSchool of Energy and Power Engineering, Lanzhou University of Technology, Lanzhou 730050, ChinaSchool of Energy and Power Engineering, Lanzhou University of Technology, Lanzhou 730050, ChinaSchool of Energy and Power Engineering, Lanzhou University of Technology, Lanzhou 730050, ChinaAs wind energy development increases, accurate wind energy forecasting helps to develop sensible power generation plans and ensure a balance between supply and demand. Machine-learning-based forecasting models possess exceptional predictive capabilities, and data manipulation prior to model training is also a key focus of this research. This study trained a deep Long Short-Term Memory (LSTM) neural network to learn the processing results of the Savitzky-Golay filter, which can avoid overfitting due to fluctuations and noise in measurements, improving the generalization performance. The optimum data frame length to match the second-order filter was determined by comparison. In a single-step prediction, the method reduced the root-mean-square error by 3.8% compared to the model trained directly with the measurements. The method also produced the smallest errors in all steps of the multi-step advance prediction. The proposed method ensures the accuracy of the forecasting and, on that basis, also improves the timeliness of the effective forecasts.https://www.mdpi.com/2076-3417/13/3/1751renewable energylong short-term memory neural networkpower predictionmulti-step prediction |
| spellingShingle | Shujun Liu Yaocong Zhang Xiaoze Du Tong Xu Jiangbo Wu Short-Term Power Prediction of Wind Turbine Applying Machine Learning and Digital Filter Applied Sciences renewable energy long short-term memory neural network power prediction multi-step prediction |
| title | Short-Term Power Prediction of Wind Turbine Applying Machine Learning and Digital Filter |
| title_full | Short-Term Power Prediction of Wind Turbine Applying Machine Learning and Digital Filter |
| title_fullStr | Short-Term Power Prediction of Wind Turbine Applying Machine Learning and Digital Filter |
| title_full_unstemmed | Short-Term Power Prediction of Wind Turbine Applying Machine Learning and Digital Filter |
| title_short | Short-Term Power Prediction of Wind Turbine Applying Machine Learning and Digital Filter |
| title_sort | short term power prediction of wind turbine applying machine learning and digital filter |
| topic | renewable energy long short-term memory neural network power prediction multi-step prediction |
| url | https://www.mdpi.com/2076-3417/13/3/1751 |
| work_keys_str_mv | AT shujunliu shorttermpowerpredictionofwindturbineapplyingmachinelearninganddigitalfilter AT yaocongzhang shorttermpowerpredictionofwindturbineapplyingmachinelearninganddigitalfilter AT xiaozedu shorttermpowerpredictionofwindturbineapplyingmachinelearninganddigitalfilter AT tongxu shorttermpowerpredictionofwindturbineapplyingmachinelearninganddigitalfilter AT jiangbowu shorttermpowerpredictionofwindturbineapplyingmachinelearninganddigitalfilter |