A novel wind power forecast diffusion model based on prior knowledge
Abstract To improve the forecast accuracy of wind power, diffusion model based on prior knowledge (DMPK) is proposed. Different from the traditional diffusion model (DM), where the noise perturbation in the diffusion or generation process is random, the noise added in DMPK is modified aiming to the...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2024-10-01
|
| Series: | IET Renewable Power Generation |
| Subjects: | |
| Online Access: | https://doi.org/10.1049/rpg2.13087 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841546491348385792 |
|---|---|
| author | Li Han Yingjie Cheng Shuo Chen Shiqi Wang Junjie Wang |
| author_facet | Li Han Yingjie Cheng Shuo Chen Shiqi Wang Junjie Wang |
| author_sort | Li Han |
| collection | DOAJ |
| description | Abstract To improve the forecast accuracy of wind power, diffusion model based on prior knowledge (DMPK) is proposed. Different from the traditional diffusion model (DM), where the noise perturbation in the diffusion or generation process is random, the noise added in DMPK is modified aiming to the characteristics of wind power signals. The distribution of wind power forecast errors is not a standard Gaussian. Wind power forecast errors are related to forecast methods, weather conditions, and other factors, containing both random signals and certain regularity. This paper adapts the Gaussian distribution to fit the historical forecast error to represent the prior knowledge of wind power. Then, the sampling distribution is derived from its relationship with the fitted prior distribution to replace the standard Gaussian in DM. Taking the prior knowledge into account during the process of noise sampling, the data in the forward process of DMPK can be guided by the distribution of historical errors for diffusion, while the generated result by the reverse process is more consistent with the actual wind power signal. Finally, the superiority of the proposed method is verified by using the wind power data from two real‐world wind farms. |
| format | Article |
| id | doaj-art-24a1a22949b14933a8187e526f26cbc8 |
| institution | Kabale University |
| issn | 1752-1416 1752-1424 |
| language | English |
| publishDate | 2024-10-01 |
| publisher | Wiley |
| record_format | Article |
| series | IET Renewable Power Generation |
| spelling | doaj-art-24a1a22949b14933a8187e526f26cbc82025-01-10T17:41:03ZengWileyIET Renewable Power Generation1752-14161752-14242024-10-0118142440245410.1049/rpg2.13087A novel wind power forecast diffusion model based on prior knowledgeLi Han0Yingjie Cheng1Shuo Chen2Shiqi Wang3Junjie Wang4School of Electrical EngineeringChina University of Mining and TechnologyXuzhouJiangsu ProvinceChinaSchool of Electrical EngineeringChina University of Mining and TechnologyXuzhouJiangsu ProvinceChinaSchool of Electrical EngineeringChina University of Mining and TechnologyXuzhouJiangsu ProvinceChinaSchool of Electrical EngineeringChina University of Mining and TechnologyXuzhouJiangsu ProvinceChinaPingdingshan Power Generation Branch SPIC Henan Electric Power Co., Ltd Zhengzhou Henan Province ChinaAbstract To improve the forecast accuracy of wind power, diffusion model based on prior knowledge (DMPK) is proposed. Different from the traditional diffusion model (DM), where the noise perturbation in the diffusion or generation process is random, the noise added in DMPK is modified aiming to the characteristics of wind power signals. The distribution of wind power forecast errors is not a standard Gaussian. Wind power forecast errors are related to forecast methods, weather conditions, and other factors, containing both random signals and certain regularity. This paper adapts the Gaussian distribution to fit the historical forecast error to represent the prior knowledge of wind power. Then, the sampling distribution is derived from its relationship with the fitted prior distribution to replace the standard Gaussian in DM. Taking the prior knowledge into account during the process of noise sampling, the data in the forward process of DMPK can be guided by the distribution of historical errors for diffusion, while the generated result by the reverse process is more consistent with the actual wind power signal. Finally, the superiority of the proposed method is verified by using the wind power data from two real‐world wind farms.https://doi.org/10.1049/rpg2.13087technological forecastingwind power |
| spellingShingle | Li Han Yingjie Cheng Shuo Chen Shiqi Wang Junjie Wang A novel wind power forecast diffusion model based on prior knowledge IET Renewable Power Generation technological forecasting wind power |
| title | A novel wind power forecast diffusion model based on prior knowledge |
| title_full | A novel wind power forecast diffusion model based on prior knowledge |
| title_fullStr | A novel wind power forecast diffusion model based on prior knowledge |
| title_full_unstemmed | A novel wind power forecast diffusion model based on prior knowledge |
| title_short | A novel wind power forecast diffusion model based on prior knowledge |
| title_sort | novel wind power forecast diffusion model based on prior knowledge |
| topic | technological forecasting wind power |
| url | https://doi.org/10.1049/rpg2.13087 |
| work_keys_str_mv | AT lihan anovelwindpowerforecastdiffusionmodelbasedonpriorknowledge AT yingjiecheng anovelwindpowerforecastdiffusionmodelbasedonpriorknowledge AT shuochen anovelwindpowerforecastdiffusionmodelbasedonpriorknowledge AT shiqiwang anovelwindpowerforecastdiffusionmodelbasedonpriorknowledge AT junjiewang anovelwindpowerforecastdiffusionmodelbasedonpriorknowledge AT lihan novelwindpowerforecastdiffusionmodelbasedonpriorknowledge AT yingjiecheng novelwindpowerforecastdiffusionmodelbasedonpriorknowledge AT shuochen novelwindpowerforecastdiffusionmodelbasedonpriorknowledge AT shiqiwang novelwindpowerforecastdiffusionmodelbasedonpriorknowledge AT junjiewang novelwindpowerforecastdiffusionmodelbasedonpriorknowledge |