Forecast Method of Distributed Photovoltaic Power Generation Based on EM-WS-CNN Neural Networks
In order to cope with the challenges of dispatching of power grids brought by large-scale distributed photovoltaic power generation related to production and consumers, a maximum expected sample weighted convolutional neural network (EM-WS-CNN) is proposed to forecast the distributed photovoltaic ou...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2022-05-01
|
| Series: | Frontiers in Energy Research |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fenrg.2022.902722/full |
| _version_ | 1828223780092116992 |
|---|---|
| author | Ruanming Huang Xiaohui Wang Fei Fei Haoen Li Enqi Wu |
| author_facet | Ruanming Huang Xiaohui Wang Fei Fei Haoen Li Enqi Wu |
| author_sort | Ruanming Huang |
| collection | DOAJ |
| description | In order to cope with the challenges of dispatching of power grids brought by large-scale distributed photovoltaic power generation related to production and consumers, a maximum expected sample weighted convolutional neural network (EM-WS-CNN) is proposed to forecast the distributed photovoltaic output. First, the distance correlation coefficient and the principal component analysis method are used to extract the comprehensive meteorological factors from the original meteorological data, and then the 6 statistical indexes of the comprehensive meteorological factors and historical power data are used as the clustering characteristics. The historical data are divided into different weather types by using the maximum expectation clustering, and the training samples are weighted based on the membership matrix. Finally, the weighted training data are used to construct the EM-WS-CNN model. In the experimental analysis, the above-mentioned method is compared with the CNN model, and the results show that the proposed method has higher accuracy and robustness. |
| first_indexed | 2024-04-12T17:13:09Z |
| format | Article |
| id | doaj.art-70735d1a7dfb4650911b9d8ac83f0d5b |
| institution | Directory Open Access Journal |
| issn | 2296-598X |
| language | English |
| last_indexed | 2024-04-12T17:13:09Z |
| publishDate | 2022-05-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Energy Research |
| spelling | doaj.art-70735d1a7dfb4650911b9d8ac83f0d5b2022-12-22T03:23:45ZengFrontiers Media S.A.Frontiers in Energy Research2296-598X2022-05-011010.3389/fenrg.2022.902722902722Forecast Method of Distributed Photovoltaic Power Generation Based on EM-WS-CNN Neural NetworksRuanming HuangXiaohui WangFei FeiHaoen LiEnqi WuIn order to cope with the challenges of dispatching of power grids brought by large-scale distributed photovoltaic power generation related to production and consumers, a maximum expected sample weighted convolutional neural network (EM-WS-CNN) is proposed to forecast the distributed photovoltaic output. First, the distance correlation coefficient and the principal component analysis method are used to extract the comprehensive meteorological factors from the original meteorological data, and then the 6 statistical indexes of the comprehensive meteorological factors and historical power data are used as the clustering characteristics. The historical data are divided into different weather types by using the maximum expectation clustering, and the training samples are weighted based on the membership matrix. Finally, the weighted training data are used to construct the EM-WS-CNN model. In the experimental analysis, the above-mentioned method is compared with the CNN model, and the results show that the proposed method has higher accuracy and robustness.https://www.frontiersin.org/articles/10.3389/fenrg.2022.902722/fulldistributed generationphotovoltaic power generation forecastEM-WS-CNNneural networkprosumer |
| spellingShingle | Ruanming Huang Xiaohui Wang Fei Fei Haoen Li Enqi Wu Forecast Method of Distributed Photovoltaic Power Generation Based on EM-WS-CNN Neural Networks Frontiers in Energy Research distributed generation photovoltaic power generation forecast EM-WS-CNN neural network prosumer |
| title | Forecast Method of Distributed Photovoltaic Power Generation Based on EM-WS-CNN Neural Networks |
| title_full | Forecast Method of Distributed Photovoltaic Power Generation Based on EM-WS-CNN Neural Networks |
| title_fullStr | Forecast Method of Distributed Photovoltaic Power Generation Based on EM-WS-CNN Neural Networks |
| title_full_unstemmed | Forecast Method of Distributed Photovoltaic Power Generation Based on EM-WS-CNN Neural Networks |
| title_short | Forecast Method of Distributed Photovoltaic Power Generation Based on EM-WS-CNN Neural Networks |
| title_sort | forecast method of distributed photovoltaic power generation based on em ws cnn neural networks |
| topic | distributed generation photovoltaic power generation forecast EM-WS-CNN neural network prosumer |
| url | https://www.frontiersin.org/articles/10.3389/fenrg.2022.902722/full |
| work_keys_str_mv | AT ruanminghuang forecastmethodofdistributedphotovoltaicpowergenerationbasedonemwscnnneuralnetworks AT xiaohuiwang forecastmethodofdistributedphotovoltaicpowergenerationbasedonemwscnnneuralnetworks AT feifei forecastmethodofdistributedphotovoltaicpowergenerationbasedonemwscnnneuralnetworks AT haoenli forecastmethodofdistributedphotovoltaicpowergenerationbasedonemwscnnneuralnetworks AT enqiwu forecastmethodofdistributedphotovoltaicpowergenerationbasedonemwscnnneuralnetworks |