A novel Wasserstein generative adversarial network for stochastic wind power output scenario generation
Abstract A novel Wasserstein generative adversarial network (WGAN) is proposed for stochastic wind power output scenario generation. Wasserstein distance with gradient penalty adapts to the gradient vanishing problem that is easy to occur in the new energy generation scenario. This model has better...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2024-12-01
|
| Series: | IET Renewable Power Generation |
| Subjects: | |
| Online Access: | https://doi.org/10.1049/rpg2.12932 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832579864289345536 |
|---|---|
| author | Xiurong Zhang Daoliang Li Xueqian Fu |
| author_facet | Xiurong Zhang Daoliang Li Xueqian Fu |
| author_sort | Xiurong Zhang |
| collection | DOAJ |
| description | Abstract A novel Wasserstein generative adversarial network (WGAN) is proposed for stochastic wind power output scenario generation. Wasserstein distance with gradient penalty adapts to the gradient vanishing problem that is easy to occur in the new energy generation scenario. This model has better robustness and generalization ability than the traditional generative adversarial network. WGAN is optimized to simulate ideal wind power scenarios. The generated data are measured by cumulative distribution function (CDF) and continuously ranked probability score to evaluate the performance of the proposed model. Compared with the probability models, the proposed model is data‐driven, that is, it can simulate wind power scenarios based on historical samples rather than probability hypothesis, and it can independently learn the space‐time correlation of wind power generation in different locations. Experiments show that the CDF curve of data generated by the proposed WGAN is highly coincident with that of real data. |
| format | Article |
| id | doaj-art-8e2d413f606d4c529a6575c1d42b279f |
| institution | Kabale University |
| issn | 1752-1416 1752-1424 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | Wiley |
| record_format | Article |
| series | IET Renewable Power Generation |
| spelling | doaj-art-8e2d413f606d4c529a6575c1d42b279f2025-01-30T12:15:53ZengWileyIET Renewable Power Generation1752-14161752-14242024-12-0118163731374210.1049/rpg2.12932A novel Wasserstein generative adversarial network for stochastic wind power output scenario generationXiurong Zhang0Daoliang Li1Xueqian Fu2National Innovation Center for Digital Fishery China Agricultural University Beijing ChinaNational Innovation Center for Digital Fishery China Agricultural University Beijing ChinaNational Innovation Center for Digital Fishery China Agricultural University Beijing ChinaAbstract A novel Wasserstein generative adversarial network (WGAN) is proposed for stochastic wind power output scenario generation. Wasserstein distance with gradient penalty adapts to the gradient vanishing problem that is easy to occur in the new energy generation scenario. This model has better robustness and generalization ability than the traditional generative adversarial network. WGAN is optimized to simulate ideal wind power scenarios. The generated data are measured by cumulative distribution function (CDF) and continuously ranked probability score to evaluate the performance of the proposed model. Compared with the probability models, the proposed model is data‐driven, that is, it can simulate wind power scenarios based on historical samples rather than probability hypothesis, and it can independently learn the space‐time correlation of wind power generation in different locations. Experiments show that the CDF curve of data generated by the proposed WGAN is highly coincident with that of real data.https://doi.org/10.1049/rpg2.12932generative adversarial networkscenario generationuncertaintyWasserstein distancewind powerwind power |
| spellingShingle | Xiurong Zhang Daoliang Li Xueqian Fu A novel Wasserstein generative adversarial network for stochastic wind power output scenario generation IET Renewable Power Generation generative adversarial network scenario generation uncertainty Wasserstein distance wind power wind power |
| title | A novel Wasserstein generative adversarial network for stochastic wind power output scenario generation |
| title_full | A novel Wasserstein generative adversarial network for stochastic wind power output scenario generation |
| title_fullStr | A novel Wasserstein generative adversarial network for stochastic wind power output scenario generation |
| title_full_unstemmed | A novel Wasserstein generative adversarial network for stochastic wind power output scenario generation |
| title_short | A novel Wasserstein generative adversarial network for stochastic wind power output scenario generation |
| title_sort | novel wasserstein generative adversarial network for stochastic wind power output scenario generation |
| topic | generative adversarial network scenario generation uncertainty Wasserstein distance wind power wind power |
| url | https://doi.org/10.1049/rpg2.12932 |
| work_keys_str_mv | AT xiurongzhang anovelwassersteingenerativeadversarialnetworkforstochasticwindpoweroutputscenariogeneration AT daoliangli anovelwassersteingenerativeadversarialnetworkforstochasticwindpoweroutputscenariogeneration AT xueqianfu anovelwassersteingenerativeadversarialnetworkforstochasticwindpoweroutputscenariogeneration AT xiurongzhang novelwassersteingenerativeadversarialnetworkforstochasticwindpoweroutputscenariogeneration AT daoliangli novelwassersteingenerativeadversarialnetworkforstochasticwindpoweroutputscenariogeneration AT xueqianfu novelwassersteingenerativeadversarialnetworkforstochasticwindpoweroutputscenariogeneration |