Wind power prediction and improvement algorithm based on multi-objective collaborative training
Under the ′dual carbon′ goal, the transformation of the power system is accelerating, and wind power prediction technology is of great significance to the construction of a new power system with a high proportion of new energy. In order to improve the accuracy and robustness of wind power prediction...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Editorial Department of Electric Power Engineering Technology
2023-11-01
|
| Series: | 电力工程技术 |
| Subjects: | |
| Online Access: | https://www.epet-info.com/dlgcjsen/article/abstract/221205704 |
| _version_ | 1797405596979298304 |
|---|---|
| author | SONG Jiakang ZHAO Jianyong SUN Haixia WANG Hualei NIAN Heng ZHANG Sen |
| author_facet | SONG Jiakang ZHAO Jianyong SUN Haixia WANG Hualei NIAN Heng ZHANG Sen |
| author_sort | SONG Jiakang |
| collection | DOAJ |
| description | Under the ′dual carbon′ goal, the transformation of the power system is accelerating, and wind power prediction technology is of great significance to the construction of a new power system with a high proportion of new energy. In order to improve the accuracy and robustness of wind power prediction, an numerical weather predicition (NWP) implicit correction algorithm based on multi-objective collaborative training is proposed. Firstly, the necessity of NWP correction and the problems of the two-step prediction method based on NWP explicit correction are analyzed. Then, aiming at the problems existing in the two-step prediction method, the optimization method based on multi-objective collaborative training uses the neural network to perform NWP implicit correction, train the model in an end-to-end manner, and realize the functions of NWP implicit correction and wind power prediction at the same time. Combined with the measured data of a wind farm, the specific calculation case analysis proves that the proposed algorithm has an improving effect on short-term, medium- and long-term wind power prediction. In addition, the algorithm only requires one network and avoids secondary calculation, saving computing and storage costs. |
| first_indexed | 2024-03-09T03:12:17Z |
| format | Article |
| id | doaj.art-d38520aa4da94426bb553233a3bc3edf |
| institution | Directory Open Access Journal |
| issn | 2096-3203 |
| language | zho |
| last_indexed | 2024-03-09T03:12:17Z |
| publishDate | 2023-11-01 |
| publisher | Editorial Department of Electric Power Engineering Technology |
| record_format | Article |
| series | 电力工程技术 |
| spelling | doaj.art-d38520aa4da94426bb553233a3bc3edf2023-12-04T00:44:16ZzhoEditorial Department of Electric Power Engineering Technology电力工程技术2096-32032023-11-0142623224010.12158/j.2096-3203.2023.06.025221205704Wind power prediction and improvement algorithm based on multi-objective collaborative trainingSONG Jiakang0ZHAO Jianyong1SUN Haixia2WANG Hualei3NIAN Heng4ZHANG Sen5State Grid Lianyungang Power Supply Company of Jiangsu Electric Power Co., Ltd., Lianyungang 222000, ChinaCollege of Electrical Engineering Zhejiang University, Hangzhou 310027, ChinaState Grid Lianyungang Power Supply Company of Jiangsu Electric Power Co., Ltd., Lianyungang 222000, ChinaState Grid Lianyungang Power Supply Company of Jiangsu Electric Power Co., Ltd., Lianyungang 222000, ChinaCollege of Electrical Engineering Zhejiang University, Hangzhou 310027, ChinaCollege of Electrical Engineering Zhejiang University, Hangzhou 310027, ChinaUnder the ′dual carbon′ goal, the transformation of the power system is accelerating, and wind power prediction technology is of great significance to the construction of a new power system with a high proportion of new energy. In order to improve the accuracy and robustness of wind power prediction, an numerical weather predicition (NWP) implicit correction algorithm based on multi-objective collaborative training is proposed. Firstly, the necessity of NWP correction and the problems of the two-step prediction method based on NWP explicit correction are analyzed. Then, aiming at the problems existing in the two-step prediction method, the optimization method based on multi-objective collaborative training uses the neural network to perform NWP implicit correction, train the model in an end-to-end manner, and realize the functions of NWP implicit correction and wind power prediction at the same time. Combined with the measured data of a wind farm, the specific calculation case analysis proves that the proposed algorithm has an improving effect on short-term, medium- and long-term wind power prediction. In addition, the algorithm only requires one network and avoids secondary calculation, saving computing and storage costs.https://www.epet-info.com/dlgcjsen/article/abstract/221205704wind power forecastingnumerical weather predicition (nwp) implicit correctionneural networksimprovement algorithmmulti-objective collaborative trainingtwo-step forecasting method |
| spellingShingle | SONG Jiakang ZHAO Jianyong SUN Haixia WANG Hualei NIAN Heng ZHANG Sen Wind power prediction and improvement algorithm based on multi-objective collaborative training 电力工程技术 wind power forecasting numerical weather predicition (nwp) implicit correction neural networks improvement algorithm multi-objective collaborative training two-step forecasting method |
| title | Wind power prediction and improvement algorithm based on multi-objective collaborative training |
| title_full | Wind power prediction and improvement algorithm based on multi-objective collaborative training |
| title_fullStr | Wind power prediction and improvement algorithm based on multi-objective collaborative training |
| title_full_unstemmed | Wind power prediction and improvement algorithm based on multi-objective collaborative training |
| title_short | Wind power prediction and improvement algorithm based on multi-objective collaborative training |
| title_sort | wind power prediction and improvement algorithm based on multi objective collaborative training |
| topic | wind power forecasting numerical weather predicition (nwp) implicit correction neural networks improvement algorithm multi-objective collaborative training two-step forecasting method |
| url | https://www.epet-info.com/dlgcjsen/article/abstract/221205704 |
| work_keys_str_mv | AT songjiakang windpowerpredictionandimprovementalgorithmbasedonmultiobjectivecollaborativetraining AT zhaojianyong windpowerpredictionandimprovementalgorithmbasedonmultiobjectivecollaborativetraining AT sunhaixia windpowerpredictionandimprovementalgorithmbasedonmultiobjectivecollaborativetraining AT wanghualei windpowerpredictionandimprovementalgorithmbasedonmultiobjectivecollaborativetraining AT nianheng windpowerpredictionandimprovementalgorithmbasedonmultiobjectivecollaborativetraining AT zhangsen windpowerpredictionandimprovementalgorithmbasedonmultiobjectivecollaborativetraining |