An algorithm with LightGBM + SVM fusion model for the assessment of dynamic security region
With the development of energy transition, the complexity of power systems’ structure, planning and operation is continuously increasing. As to quickly and accurately assess the dynamic security region of power system, there are prominent problems with traditional manual analysis method, i.e. the ru...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
EDP Sciences
2021-01-01
|
| Series: | E3S Web of Conferences |
| Online Access: | https://www.e3s-conferences.org/articles/e3sconf/pdf/2021/32/e3sconf_posei2021_02022.pdf |
| id |
doaj-3a5a5c11d589400cbdeba326bbf302e7 |
|---|---|
| record_format |
Article |
| spelling |
doaj-3a5a5c11d589400cbdeba326bbf302e72021-05-28T12:41:52ZengEDP SciencesE3S Web of Conferences2267-12422021-01-012560202210.1051/e3sconf/202125602022e3sconf_posei2021_02022An algorithm with LightGBM + SVM fusion model for the assessment of dynamic security regionLiang Lulu0Hu Wei1Zhang Yiwei2Ma Kun3Gu Yujia4Tian Bei5Li Hongqiang6Department of Electrical Engineering, Tsinghua UniversityDepartment of Electrical Engineering, Tsinghua UniversityDepartment of Electrical Engineering, Tsinghua UniversityDepartment of Electrical Engineering, Tsinghua UniversityState Grid Ningxia Electric Power Co. Ltd.State Grid Ningxia Electric Power Co. Ltd.State Grid Ningxia Electric Power Co. Ltd.With the development of energy transition, the complexity of power systems’ structure, planning and operation is continuously increasing. As to quickly and accurately assess the dynamic security region of power system, there are prominent problems with traditional manual analysis method, i.e. the rules’ roughness and a low calculation efficiency while data mining approach could provide a new way to get off such problems. Considering that the performance of SVM algorithm depends on feature selection and the LightGBM, a fast and efficient classification algorithm, can be used for feature selection, this paper proposes a new algorithm based on a fusion model. With the CEPRI-36 bus power system, the results of different algorithms are compared and the proposed algorithm verified.https://www.e3s-conferences.org/articles/e3sconf/pdf/2021/32/e3sconf_posei2021_02022.pdf |
| collection |
DOAJ |
| language |
English |
| format |
Article |
| sources |
DOAJ |
| author |
Liang Lulu Hu Wei Zhang Yiwei Ma Kun Gu Yujia Tian Bei Li Hongqiang |
| spellingShingle |
Liang Lulu Hu Wei Zhang Yiwei Ma Kun Gu Yujia Tian Bei Li Hongqiang An algorithm with LightGBM + SVM fusion model for the assessment of dynamic security region E3S Web of Conferences |
| author_facet |
Liang Lulu Hu Wei Zhang Yiwei Ma Kun Gu Yujia Tian Bei Li Hongqiang |
| author_sort |
Liang Lulu |
| title |
An algorithm with LightGBM + SVM fusion model for the assessment of dynamic security region |
| title_short |
An algorithm with LightGBM + SVM fusion model for the assessment of dynamic security region |
| title_full |
An algorithm with LightGBM + SVM fusion model for the assessment of dynamic security region |
| title_fullStr |
An algorithm with LightGBM + SVM fusion model for the assessment of dynamic security region |
| title_full_unstemmed |
An algorithm with LightGBM + SVM fusion model for the assessment of dynamic security region |
| title_sort |
algorithm with lightgbm + svm fusion model for the assessment of dynamic security region |
| publisher |
EDP Sciences |
| series |
E3S Web of Conferences |
| issn |
2267-1242 |
| publishDate |
2021-01-01 |
| description |
With the development of energy transition, the complexity of power systems’ structure, planning and operation is continuously increasing. As to quickly and accurately assess the dynamic security region of power system, there are prominent problems with traditional manual analysis method, i.e. the rules’ roughness and a low calculation efficiency while data mining approach could provide a new way to get off such problems. Considering that the performance of SVM algorithm depends on feature selection and the LightGBM, a fast and efficient classification algorithm, can be used for feature selection, this paper proposes a new algorithm based on a fusion model. With the CEPRI-36 bus power system, the results of different algorithms are compared and the proposed algorithm verified. |
| url |
https://www.e3s-conferences.org/articles/e3sconf/pdf/2021/32/e3sconf_posei2021_02022.pdf |
| work_keys_str_mv |
AT lianglulu analgorithmwithlightgbmsvmfusionmodelfortheassessmentofdynamicsecurityregion AT huwei analgorithmwithlightgbmsvmfusionmodelfortheassessmentofdynamicsecurityregion AT zhangyiwei analgorithmwithlightgbmsvmfusionmodelfortheassessmentofdynamicsecurityregion AT makun analgorithmwithlightgbmsvmfusionmodelfortheassessmentofdynamicsecurityregion AT guyujia analgorithmwithlightgbmsvmfusionmodelfortheassessmentofdynamicsecurityregion AT tianbei analgorithmwithlightgbmsvmfusionmodelfortheassessmentofdynamicsecurityregion AT lihongqiang analgorithmwithlightgbmsvmfusionmodelfortheassessmentofdynamicsecurityregion AT lianglulu algorithmwithlightgbmsvmfusionmodelfortheassessmentofdynamicsecurityregion AT huwei algorithmwithlightgbmsvmfusionmodelfortheassessmentofdynamicsecurityregion AT zhangyiwei algorithmwithlightgbmsvmfusionmodelfortheassessmentofdynamicsecurityregion AT makun algorithmwithlightgbmsvmfusionmodelfortheassessmentofdynamicsecurityregion AT guyujia algorithmwithlightgbmsvmfusionmodelfortheassessmentofdynamicsecurityregion AT tianbei algorithmwithlightgbmsvmfusionmodelfortheassessmentofdynamicsecurityregion AT lihongqiang algorithmwithlightgbmsvmfusionmodelfortheassessmentofdynamicsecurityregion |
| _version_ |
1721423880618246144 |