EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Diffusion Model with Multi-Source Data for Day-Ahead Renewable Energy Scenario Generation

Lin Chen, Xinran Liu, Quanqi Chen, Guinan Ye, Wen Liu, Xiaotong Dai

Sustainability · 23.07.2026 · 18 (15) · 7526

DOI: 10.3390/su18157526 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sustainability, online erschienen am 23.07.2026. Verfasst von Lin Chen und 5 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 32 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Science and Technology Project of Guangxi Power Grid Co., Ltd..

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

High-quality renewable energy (RE) scenario generation is essential for secure, reliable, and economic power system operation under high RE penetration. To address the limitations of existing methods in preserving scenario fidelity, diversity, spatiotemporal dependence, and engineering consistency, this paper proposes a three-stage framework that combines a variational autoencoder (VAE) with a conditional latent diffusion model (CLDM), hereafter referred to as VAE-CLDM, for day-ahead renewable energy scenario generation. First, multi-source features are constructed by integrating renewable power outputs, meteorological variables, temporal lag information, and spatial correlation characteristics among wind farms and photovoltaic stations. Then, VAE compresses the high-dimensional features into a compact latent space while retaining key statistical and spatiotemporal information. Based on this latent representation, a CLDM generates realistic scenarios by progressively denoising random noise under meteorological conditions. A spatiotemporal feature modeling strategy is incorporated to better represent temporal fluctuations and inter-site correlations, while a diversity regulation factor is selected on the validation set to balance scenario fidelity and tail-event coverage. Finally, the generated scenarios are reconstructed into the physical space and checked using output-bound and ramp-consistency correction to improve their practical usability. Results on the open dataset released by the Chinese State Grid Renewable Energy Generation Forecasting Competition show that the proposed framework achieves the lowest root mean square error (RMSE), mean absolute error (MAE), and maximum mean discrepancy (MMD) among the tested models on the training-statistics-standardized renewable-power benchmark, with RMSE of 0.3013±0.0022, MAE of 0.3636±0.0010, and MMD of 0.04269±0.00040. After post-correction, lower- and upper-bound violations are reduced to 0.00%, and the ramp-violation rate is reduced to 0.08%, indicating that the proposed VAE-CLDM can provide useful scenario inputs for day-ahead dispatch and risk assessment in renewable-dominated power systems.

Förderung

  • Science and Technology Project of Guangxi Power Grid Co., Ltd.

Zitieren

APA

Chen, L., Liu, X., Chen, Q., Ye, G., Liu, W., & Dai, X. (2026). Diffusion Model with Multi-Source Data for Day-Ahead Renewable Energy Scenario Generation. Sustainability, 18(15), 7526. https://doi.org/10.3390/su18157526

Vancouver

Chen L, Liu X, Chen Q, Ye G, Liu W, Dai X. Diffusion Model with Multi-Source Data for Day-Ahead Renewable Energy Scenario Generation. Sustainability. 2026;18(15):7526. doi:10.3390/su18157526

BibTeX
@article{Chen2026,
  author = {Chen, Lin and Liu, Xinran and Chen, Quanqi and Ye, Guinan and Liu, Wen and Dai, Xiaotong},
  title = {Diffusion Model with Multi-Source Data for Day-Ahead Renewable Energy Scenario Generation},
  journal = {Sustainability},
  year = {2026},
  volume = {18},
  number = {15},
  pages = {7526},
  doi = {10.3390/su18157526}
}
Kostenlos starten →