A Spatiotemporal Coupling Calculation-Based Short-Term Wind Farm Cluster Power Prediction Method
Accurate short-term wind power prediction is of great significance to the real-time dispatching of power systems and the development of wind power generation plans. However, existing methods for wind power prediction have the following problems: 1) some studies aim at predicting wind power for a sin...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10325487/ |
| _version_ | 1797321111796449280 |
|---|---|
| author | Haochen Li Liqun Liu Qiusheng He |
| author_facet | Haochen Li Liqun Liu Qiusheng He |
| author_sort | Haochen Li |
| collection | DOAJ |
| description | Accurate short-term wind power prediction is of great significance to the real-time dispatching of power systems and the development of wind power generation plans. However, existing methods for wind power prediction have the following problems: 1) some studies aim at predicting wind power for a single wind farm, ignoring the correlations of the adjacent wind farms; 2) many studies tend to convert wind speed forecast results to wind power, increasing the conversion error; 3) almost all studies place emphasis on the capture of spatiotemporal features, neglecting the influence of spatiotemporal coupling. Therefore, to solve the above questions, this work proposes an adaptive graph neural network based on spatiotemporal attention calculation for short-term wind farm cluster power prediction, using only wind power data. Firstly, a dynamic undirected graph is established to sufficiently learn prior knowledge of spatial relationships. Next, the spatiotemporal coupling relationship and global temporal correlation between data can be computed by performing spatiotemporal cross-attention and temporal self-attention, respectively. Finally, a novel hybrid loss function is proposed to optimize the prediction model accurately. In a case study, compared with other benchmark methods, the proposed method shows excellent overall performance in predicting wind power. |
| first_indexed | 2024-03-08T04:52:49Z |
| format | Article |
| id | doaj.art-b03c3d8983784a14a925a8996f2aa87b |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-03-08T04:52:49Z |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-b03c3d8983784a14a925a8996f2aa87b2024-02-08T00:00:36ZengIEEEIEEE Access2169-35362023-01-011113141813143410.1109/ACCESS.2023.333562910325487A Spatiotemporal Coupling Calculation-Based Short-Term Wind Farm Cluster Power Prediction MethodHaochen Li0Liqun Liu1https://orcid.org/0009-0007-9444-2545Qiusheng He2School of Electronic Information Engineering, Taiyuan University of Science and Technology, Taiyuan, ChinaSchool of Electronic Information Engineering, Taiyuan University of Science and Technology, Taiyuan, ChinaSchool of Electronic Information Engineering, Taiyuan University of Science and Technology, Taiyuan, ChinaAccurate short-term wind power prediction is of great significance to the real-time dispatching of power systems and the development of wind power generation plans. However, existing methods for wind power prediction have the following problems: 1) some studies aim at predicting wind power for a single wind farm, ignoring the correlations of the adjacent wind farms; 2) many studies tend to convert wind speed forecast results to wind power, increasing the conversion error; 3) almost all studies place emphasis on the capture of spatiotemporal features, neglecting the influence of spatiotemporal coupling. Therefore, to solve the above questions, this work proposes an adaptive graph neural network based on spatiotemporal attention calculation for short-term wind farm cluster power prediction, using only wind power data. Firstly, a dynamic undirected graph is established to sufficiently learn prior knowledge of spatial relationships. Next, the spatiotemporal coupling relationship and global temporal correlation between data can be computed by performing spatiotemporal cross-attention and temporal self-attention, respectively. Finally, a novel hybrid loss function is proposed to optimize the prediction model accurately. In a case study, compared with other benchmark methods, the proposed method shows excellent overall performance in predicting wind power.https://ieeexplore.ieee.org/document/10325487/Short-term wind power predictionspatiotemporal couplingadaptive graph neural networkattention calculation |
| spellingShingle | Haochen Li Liqun Liu Qiusheng He A Spatiotemporal Coupling Calculation-Based Short-Term Wind Farm Cluster Power Prediction Method IEEE Access Short-term wind power prediction spatiotemporal coupling adaptive graph neural network attention calculation |
| title | A Spatiotemporal Coupling Calculation-Based Short-Term Wind Farm Cluster Power Prediction Method |
| title_full | A Spatiotemporal Coupling Calculation-Based Short-Term Wind Farm Cluster Power Prediction Method |
| title_fullStr | A Spatiotemporal Coupling Calculation-Based Short-Term Wind Farm Cluster Power Prediction Method |
| title_full_unstemmed | A Spatiotemporal Coupling Calculation-Based Short-Term Wind Farm Cluster Power Prediction Method |
| title_short | A Spatiotemporal Coupling Calculation-Based Short-Term Wind Farm Cluster Power Prediction Method |
| title_sort | spatiotemporal coupling calculation based short term wind farm cluster power prediction method |
| topic | Short-term wind power prediction spatiotemporal coupling adaptive graph neural network attention calculation |
| url | https://ieeexplore.ieee.org/document/10325487/ |
| work_keys_str_mv | AT haochenli aspatiotemporalcouplingcalculationbasedshorttermwindfarmclusterpowerpredictionmethod AT liqunliu aspatiotemporalcouplingcalculationbasedshorttermwindfarmclusterpowerpredictionmethod AT qiushenghe aspatiotemporalcouplingcalculationbasedshorttermwindfarmclusterpowerpredictionmethod AT haochenli spatiotemporalcouplingcalculationbasedshorttermwindfarmclusterpowerpredictionmethod AT liqunliu spatiotemporalcouplingcalculationbasedshorttermwindfarmclusterpowerpredictionmethod AT qiushenghe spatiotemporalcouplingcalculationbasedshorttermwindfarmclusterpowerpredictionmethod |