Extraction of typical combined output scenarios of wind-solar-hydropower generation based on deep embedding clustering
It is a prerequisite for resource characteristics analysis and scheduling optimization research to screen out the representative typical scenarios of wind-solar-hydropower integrated generation systems. Due to the influence of the “dimension effect”， traditional clustering algorithms cannot be direc...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
zhejiang electric power
2023-04-01
|
| Series: | Zhejiang dianli |
| Subjects: | |
| Online Access: | https://zjdl.cbpt.cnki.net/WKE3/WebPublication/paperDigest.aspx?paperID=ef58a7e3-5842-4539-b8c2-d25b8dcc1105 |
| _version_ | 1797833238946775040 |
|---|---|
| author | TANG Yajie YAN Jie LI Yuhao GONG Diyang DU Qianyun YE Biqi |
| author_facet | TANG Yajie YAN Jie LI Yuhao GONG Diyang DU Qianyun YE Biqi |
| author_sort | TANG Yajie |
| collection | DOAJ |
| description | It is a prerequisite for resource characteristics analysis and scheduling optimization research to screen out the representative typical scenarios of wind-solar-hydropower integrated generation systems. Due to the influence of the “dimension effect”， traditional clustering algorithms cannot be directly applied to high-dimensional data clustering， and the existing technical route based on “dimension reduction before clustering” cannot guarantee that low-dimensional features after dimensionality reduction are suitable for clustering tasks， resulting in unstable clustering results. In view of the existing problems， this paper proposes a method for extracting typical output scenarios of wind-solar-hydropower based on DEC （deep embedding clustering）. The method can realize high-dimensional output data clustering and avoid that low-dimensional features after dimensionality reduction are not suitable for clustering tasks. First， with the help of the nonlinear representation ability of the stacked autoencoder， the high-dimensional wind-solar-hydropower combined output data is deeply represented to achieve data dimensionality reduction. Then， the K-means clustering method is used to cluster the deep low-dimensional features， and the stacked encoder is optimized and adjusted at the same time in the clustering process to obtain the low-dimensional wind-solar-hydropower combined output feature suitable for the clustering space. Moreover， the precise division of wind-solar-hydropower combined output scenarios is realized. Finally， the DEC is performed on the wind-solar-hydropower output data of a region in south China. The PCA-K-means algorithm is used to set up a comparison example to verify the effectiveness of the DEC in selecting typical combined output scenarios of wind-solar-hydropower generation. |
| first_indexed | 2024-04-09T14:20:07Z |
| format | Article |
| id | doaj.art-e9b9b23ed31a462fa90fcb229330567b |
| institution | Directory Open Access Journal |
| issn | 1007-1881 |
| language | zho |
| last_indexed | 2024-04-09T14:20:07Z |
| publishDate | 2023-04-01 |
| publisher | zhejiang electric power |
| record_format | Article |
| series | Zhejiang dianli |
| spelling | doaj.art-e9b9b23ed31a462fa90fcb229330567b2023-05-05T00:41:08Zzhozhejiang electric powerZhejiang dianli1007-18812023-04-01424364410.19585/j.zjdl.2023040051007-1881（2023）04-0036-09Extraction of typical combined output scenarios of wind-solar-hydropower generation based on deep embedding clusteringTANG Yajie0YAN Jie1LI Yuhao2GONG Diyang3DU Qianyun4YE Biqi5State Grid Zhejiang Electric Power Co., Ltd. Research Institute, Hangzhou 310014, ChinaState Key Laboratory of Alternate Electrical Power System With Renewable Energy Sources (North China Electric Power University), Beijing 102206, ChinaState Key Laboratory of Alternate Electrical Power System With Renewable Energy Sources (North China Electric Power University), Beijing 102206, ChinaState Grid Zhejiang Electric Power Co., Ltd. Research Institute, Hangzhou 310014, ChinaState Grid Lishui Power Supply Company, Lishui, Zhejiang 323000, ChinaState Grid Lishui Power Supply Company, Lishui, Zhejiang 323000, ChinaIt is a prerequisite for resource characteristics analysis and scheduling optimization research to screen out the representative typical scenarios of wind-solar-hydropower integrated generation systems. Due to the influence of the “dimension effect”， traditional clustering algorithms cannot be directly applied to high-dimensional data clustering， and the existing technical route based on “dimension reduction before clustering” cannot guarantee that low-dimensional features after dimensionality reduction are suitable for clustering tasks， resulting in unstable clustering results. In view of the existing problems， this paper proposes a method for extracting typical output scenarios of wind-solar-hydropower based on DEC （deep embedding clustering）. The method can realize high-dimensional output data clustering and avoid that low-dimensional features after dimensionality reduction are not suitable for clustering tasks. First， with the help of the nonlinear representation ability of the stacked autoencoder， the high-dimensional wind-solar-hydropower combined output data is deeply represented to achieve data dimensionality reduction. Then， the K-means clustering method is used to cluster the deep low-dimensional features， and the stacked encoder is optimized and adjusted at the same time in the clustering process to obtain the low-dimensional wind-solar-hydropower combined output feature suitable for the clustering space. Moreover， the precise division of wind-solar-hydropower combined output scenarios is realized. Finally， the DEC is performed on the wind-solar-hydropower output data of a region in south China. The PCA-K-means algorithm is used to set up a comparison example to verify the effectiveness of the DEC in selecting typical combined output scenarios of wind-solar-hydropower generation.https://zjdl.cbpt.cnki.net/WKE3/WebPublication/paperDigest.aspx?paperID=ef58a7e3-5842-4539-b8c2-d25b8dcc1105wind-solar-hydropower integrationtypical scenariosdeep embedding clusteringdimensionality reductionfeature extraction |
| spellingShingle | TANG Yajie YAN Jie LI Yuhao GONG Diyang DU Qianyun YE Biqi Extraction of typical combined output scenarios of wind-solar-hydropower generation based on deep embedding clustering Zhejiang dianli wind-solar-hydropower integration typical scenarios deep embedding clustering dimensionality reduction feature extraction |
| title | Extraction of typical combined output scenarios of wind-solar-hydropower generation based on deep embedding clustering |
| title_full | Extraction of typical combined output scenarios of wind-solar-hydropower generation based on deep embedding clustering |
| title_fullStr | Extraction of typical combined output scenarios of wind-solar-hydropower generation based on deep embedding clustering |
| title_full_unstemmed | Extraction of typical combined output scenarios of wind-solar-hydropower generation based on deep embedding clustering |
| title_short | Extraction of typical combined output scenarios of wind-solar-hydropower generation based on deep embedding clustering |
| title_sort | extraction of typical combined output scenarios of wind solar hydropower generation based on deep embedding clustering |
| topic | wind-solar-hydropower integration typical scenarios deep embedding clustering dimensionality reduction feature extraction |
| url | https://zjdl.cbpt.cnki.net/WKE3/WebPublication/paperDigest.aspx?paperID=ef58a7e3-5842-4539-b8c2-d25b8dcc1105 |
| work_keys_str_mv | AT tangyajie extractionoftypicalcombinedoutputscenariosofwindsolarhydropowergenerationbasedondeepembeddingclustering AT yanjie extractionoftypicalcombinedoutputscenariosofwindsolarhydropowergenerationbasedondeepembeddingclustering AT liyuhao extractionoftypicalcombinedoutputscenariosofwindsolarhydropowergenerationbasedondeepembeddingclustering AT gongdiyang extractionoftypicalcombinedoutputscenariosofwindsolarhydropowergenerationbasedondeepembeddingclustering AT duqianyun extractionoftypicalcombinedoutputscenariosofwindsolarhydropowergenerationbasedondeepembeddingclustering AT yebiqi extractionoftypicalcombinedoutputscenariosofwindsolarhydropowergenerationbasedondeepembeddingclustering |