Journal article · 2025 · Open access

Learning Residual Distributions with Diffusion Models for Probabilistic Wind Power Forecasting

Fuhao Chen, Linyue Gao

Energies, 18(16), 4226 · Published 8 August 2025 · DOI 10.3390/en18164226

Free PDFView at the publisherCite this paper

In brief

“Learning Residual Distributions with Diffusion Models for Probabilistic Wind Power Forecasting” is a 2025 journal article by Fuhao Chen and Linyue Gao, published in Energies. OpenAlex counts 10 citations as of 16 November 2026. It is open access under a CC BY licence: the full text is free to read at Energies.

Citations
10
Most cited in
2026 (9)
Field-weighted impact
1.96
References
26
Authors
2

Abstract

Accurate and uncertainty-aware wind power forecasting is essential for reliable and cost-effective power system operations. This paper presents a novel probabilistic forecasting framework based on diffusion probabilistic models. We adopted a two-stage modeling strategy—a deterministic predictor first generates baseline forecasts, and a conditional diffusion model then learns the distribution of residual errors. Such a two-stage decoupling strategy improves learning efficiency and sharpens uncertainty estimation. We employed the elucidated diffusion model (EDM) to enable flexible noise control and enhance calibration, stability, and expressiveness. For the generative backbone, we introduced a time-series-specific diffusion Transformer (TimeDiT) that incorporates modular conditioning to separately fuse numerical weather prediction (NWP) inputs, noise, and temporal features. The proposed method was evaluated using the public database from ten wind farms in the Global Energy Forecasting Competition 2014 (GEFCom2014). We further compared our approach with two popular baseline models, i.e., a distribution parameter regression model and a generative adversarial network (GAN)-based model. Results showed that our method consistently achieves superior performance in both deterministic metrics and probabilistic accuracy, offering better forecast calibration and sharper distributions.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Chen, F., & Gao, L. (2025). Learning Residual Distributions with Diffusion Models for Probabilistic Wind Power Forecasting. Energies, 18(16), 4226. https://doi.org/10.3390/en18164226

MLA 9

Chen, Fuhao, and Linyue Gao. “Learning Residual Distributions with Diffusion Models for Probabilistic Wind Power Forecasting.” Energies, vol. 18, no. 16, 2025, p. 4226. https://doi.org/10.3390/en18164226.

Chicago

Chen, Fuhao and Linyue Gao. 2025. “Learning Residual Distributions with Diffusion Models for Probabilistic Wind Power Forecasting.” Energies 18 (16): 4226. https://doi.org/10.3390/en18164226.

Harvard

Chen, F. and Gao, L. (2025) ‘Learning Residual Distributions with Diffusion Models for Probabilistic Wind Power Forecasting’, Energies, 18(16), p. 4226. doi:10.3390/en18164226.

IEEE

F. Chen and L. Gao, “Learning Residual Distributions with Diffusion Models for Probabilistic Wind Power Forecasting,” Energies, vol. 18, no. 16, p. 4226, 2025, doi: 10.3390/en18164226.

BibTeX

@article{chen2025learning,
  title     = {{Learning Residual Distributions with Diffusion Models for Probabilistic Wind Power Forecasting}},
  author    = {Chen, Fuhao and Gao, Linyue},
  journal   = {Energies},
  year      = {2025},
  volume    = {18},
  number    = {16},
  pages     = {4226},
  doi       = {10.3390/en18164226},
  url       = {https://doi.org/10.3390/en18164226}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Topic and keywords

Physical Sciences › Engineering › Electrical and Electronic Engineering › Energy Load and Power Forecasting

  • probabilistic wind power forecasting
  • diffusion probabilistic models
  • uncertainty estimation
  • two-stage forecasting
  • diffusion transformer
  • forecast calibration

Work with this paper

Most-cited papers in Engineering

All highly cited Engineering papers

Questions about this paper

How do I cite this paper in APA style?

Chen, F., & Gao, L. (2025). Learning Residual Distributions with Diffusion Models for Probabilistic Wind Power Forecasting. Energies, 18(16), 4226. https://doi.org/10.3390/en18164226

How many times has this paper been cited?

10 times, according to OpenAlex on 16 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

Yes. It is open access: read the free full text at Energies.

Who wrote this paper?

Fuhao Chen, Linyue Gao.

What is the DOI of this paper?

10.3390/en18164226. The permanent link is https://doi.org/10.3390/en18164226.

Bibliographic data from OpenAlex (CC0), last checked 16 November 2026. ResearchGuru does not host this paper; the links go to the publisher or the repository that does.