Diffusion‐based conditional wind power forecasting via channel attention
Abstract Wind energy is one of the most significant renewable sources of energy while accurate and reliable wind power forecasting methods may greatly benefit power system planning and scheduling. Recently, many machine learning algorithms have shown significant advantages in how to extract temporal...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2024-02-01
|
| Series: | IET Renewable Power Generation |
| Subjects: | |
| Online Access: | https://doi.org/10.1049/rpg2.12825 |
| _version_ | 1827341470752833536 |
|---|---|
| author | Hongqiao Peng Hui Sun Shuxin Luo Zhengmin Zuo Shixu Zhang Zhixian Wang Yi Wang |
| author_facet | Hongqiao Peng Hui Sun Shuxin Luo Zhengmin Zuo Shixu Zhang Zhixian Wang Yi Wang |
| author_sort | Hongqiao Peng |
| collection | DOAJ |
| description | Abstract Wind energy is one of the most significant renewable sources of energy while accurate and reliable wind power forecasting methods may greatly benefit power system planning and scheduling. Recently, many machine learning algorithms have shown significant advantages in how to extract temporal features for wind power forecasting. However, wind power curves in the time domain frequently display intermittent features and significant uncertainty, which is not favorable to precise and reliable forecasting. In this paper, the Diffusion and Channel Attention‐based Wind Power Forecasting (DC‐WPF) framework is proposed, which transforms wind power data into the frequency domain while applying advanced channel attention techniques to aid the model in capturing the frequency domain information and ultimately enhancing accuracy. With high‐accuracy results, DC‐WPF then proposes a diffusion‐based framework to transform the point forecasting results into probabilistic forecasts to capture the uncertainty. Finally, extensive experiments on six wind power plants show that our method can improve the point forecasting accuracy of wind power and provide advanced probabilistic forecasts at a multi‐time scale. |
| first_indexed | 2024-03-07T21:41:29Z |
| format | Article |
| id | doaj.art-583722a25e864875b3c1bb66280a3fdb |
| institution | Directory Open Access Journal |
| issn | 1752-1416 1752-1424 |
| language | English |
| last_indexed | 2024-03-07T21:41:29Z |
| publishDate | 2024-02-01 |
| publisher | Wiley |
| record_format | Article |
| series | IET Renewable Power Generation |
| spelling | doaj.art-583722a25e864875b3c1bb66280a3fdb2024-02-26T08:05:21ZengWileyIET Renewable Power Generation1752-14161752-14242024-02-0118330632010.1049/rpg2.12825Diffusion‐based conditional wind power forecasting via channel attentionHongqiao Peng0Hui Sun1Shuxin Luo2Zhengmin Zuo3Shixu Zhang4Zhixian Wang5Yi Wang6Planning Research Center of Guangdong Power Grid Corporation CSG Guangzhou Guangdong Province ChinaPlanning Research Center of Guangdong Power Grid Corporation CSG Guangzhou Guangdong Province ChinaPlanning Research Center of Guangdong Power Grid Corporation CSG Guangzhou Guangdong Province ChinaPlanning Research Center of Guangdong Power Grid Corporation CSG Guangzhou Guangdong Province ChinaTsinghua Sichuan Energy Internet Research Institute, Building 5, Area A, Tianfu Elite Center, Science City Chengdu Sichuan ChinaDepartment of Electrical and Electronic Engineering The University of Hong Kong Hong Kong Special Administrative Region of China ChinaDepartment of Electrical and Electronic Engineering The University of Hong Kong Hong Kong Special Administrative Region of China ChinaAbstract Wind energy is one of the most significant renewable sources of energy while accurate and reliable wind power forecasting methods may greatly benefit power system planning and scheduling. Recently, many machine learning algorithms have shown significant advantages in how to extract temporal features for wind power forecasting. However, wind power curves in the time domain frequently display intermittent features and significant uncertainty, which is not favorable to precise and reliable forecasting. In this paper, the Diffusion and Channel Attention‐based Wind Power Forecasting (DC‐WPF) framework is proposed, which transforms wind power data into the frequency domain while applying advanced channel attention techniques to aid the model in capturing the frequency domain information and ultimately enhancing accuracy. With high‐accuracy results, DC‐WPF then proposes a diffusion‐based framework to transform the point forecasting results into probabilistic forecasts to capture the uncertainty. Finally, extensive experiments on six wind power plants show that our method can improve the point forecasting accuracy of wind power and provide advanced probabilistic forecasts at a multi‐time scale.https://doi.org/10.1049/rpg2.12825artificial intelligencedata miningwind power |
| spellingShingle | Hongqiao Peng Hui Sun Shuxin Luo Zhengmin Zuo Shixu Zhang Zhixian Wang Yi Wang Diffusion‐based conditional wind power forecasting via channel attention IET Renewable Power Generation artificial intelligence data mining wind power |
| title | Diffusion‐based conditional wind power forecasting via channel attention |
| title_full | Diffusion‐based conditional wind power forecasting via channel attention |
| title_fullStr | Diffusion‐based conditional wind power forecasting via channel attention |
| title_full_unstemmed | Diffusion‐based conditional wind power forecasting via channel attention |
| title_short | Diffusion‐based conditional wind power forecasting via channel attention |
| title_sort | diffusion based conditional wind power forecasting via channel attention |
| topic | artificial intelligence data mining wind power |
| url | https://doi.org/10.1049/rpg2.12825 |
| work_keys_str_mv | AT hongqiaopeng diffusionbasedconditionalwindpowerforecastingviachannelattention AT huisun diffusionbasedconditionalwindpowerforecastingviachannelattention AT shuxinluo diffusionbasedconditionalwindpowerforecastingviachannelattention AT zhengminzuo diffusionbasedconditionalwindpowerforecastingviachannelattention AT shixuzhang diffusionbasedconditionalwindpowerforecastingviachannelattention AT zhixianwang diffusionbasedconditionalwindpowerforecastingviachannelattention AT yiwang diffusionbasedconditionalwindpowerforecastingviachannelattention |