IDEAS home Printed from https://ideas.repec.org/a/eee/appene/v409y2026ics0306261926001248.html

GEV distribution-enhanced Fourier diffusion model for extreme value capture in day-ahead photovoltaic scenario generation

Author

Listed:
  • Zhang, Chunyu
  • Fu, Xueqian
  • Yang, Dechang
  • Zhang, Pei
  • Zhang, Youmin

Abstract

Day-ahead photovoltaic (PV) scenario generation is a critical task in the field of renewable energy, especially for fine-scale temporal tasks such as economic dispatch planning for the day ahead, optimization of unit operation commitments, and participation in electricity markets. However, existing research on PV scenario generation primarily focuses on capturing the global statistical characteristics of the dataset and simulating its temporal characteristics, with significant limitations in modeling extreme events. This paper proposes a novel day-ahead PV scenario generation method based on a Generalized Extreme Value (GEV) enhanced Denoising Diffusion Probabilistic Model (DDPM) combined with Fourier operators. The proposed method is designed to effectively capture extreme value features in PV power data, particularly the generation of peak power values. Firstly, we integrate the GEV distribution into the DDPM framework to guarantee the realism and accuracy of the generated data in both the overall distribution and extreme events. Secondly, to improve the noise prediction accuracy of the reverse denoising network, we introduce a Fourier operator-based denoising network. This network leverages Fourier transforms to extract features in the frequency domain, boosting the model's effectiveness in identifying the temporal dynamics of PV power data. Finally, to conduct an in-depth evaluation of the generated data quality, we propose a multi-faceted evaluation approach that considers both deterministic and uncertainty assessments, providing a thorough evaluation of the accuracy and reliability of the generated data. Experimental results show that the proposed method achieves the lowest MAE (0.12 and 0.05), RMSE (0.23 and 0.08), and the highest R2 (0.95 and 0.94) on the Hebei and DKASC datasets, respectively, outperforming all benchmark models. Moreover, it demonstrates strong robustness in both deterministic and uncertainty evaluations, indicating its superior ability to generate realistic and reliable day-ahead PV scenarios, particularly under extreme conditions.

Suggested Citation

  • Zhang, Chunyu & Fu, Xueqian & Yang, Dechang & Zhang, Pei & Zhang, Youmin, 2026. "GEV distribution-enhanced Fourier diffusion model for extreme value capture in day-ahead photovoltaic scenario generation," Applied Energy, Elsevier, vol. 409(C).
    • Handle: RePEc:eee:appene:v:409:y:2026:i:c:s0306261926001248
    DOI: 10.1016/j.apenergy.2026.127472
    as

    Download full text from publisher

    File URL: http://www.sciencedirect.com/science/article/pii/S0306261926001248
    Download Restriction: Full text for ScienceDirect subscribers only
    File URL: https://libkey.io/10.1016/j.apenergy.2026.127472?utm_source=ideas
    LibKey link: if access is restricted and if your library uses this service, LibKey will redirect you to where you can use your library subscription to access this item
    ---><---

    As the access to this document is restricted, you may want to

    for a different version of it.

    References listed on IDEAS

    as
    1. Chenglong Xu & Peidong Xu & Yuxin Dai & Shi Su & Luxi Zhang & Jun Zhang & Yuyang Bai & Tianlu Gao & Qingyang Xie & Lei Shang & Wenzhong Gao, 2025. "A Two-Stage Generative Architecture for Renewable Scenario Generation Based on Temporal Scenario Representation and Diffusion Models," Energies, MDPI, vol. 18(5), pages 1-21, March.
    2. Li, Zilu & Peng, Xiangang & Cui, Wenbo & Xu, Yilin & Liu, Jianan & Yuan, Haoliang & Lai, Chun Sing & Lai, Loi Lei, 2024. "A novel scenario generation method of renewable energy using improved VAEGAN with controllable interpretable features," Applied Energy, Elsevier, vol. 363(C).
    3. Kun Zheng & Zhiyuan Sun & Yi Song & Chen Zhang & Chunyu Zhang & Fuhao Chang & Dechang Yang & Xueqian Fu, 2025. "Stochastic Scenario Generation Methods for Uncertainty in Wind and Photovoltaic Power Outputs: A Comprehensive Review," Energies, MDPI, vol. 18(3), pages 1-31, January.
    4. Zhang, Hanyu & Zandehshahvar, Reza & Tanneau, Mathieu & Van Hentenryck, Pascal, 2025. "Weather-informed probabilistic forecasting and scenario generation in power systems," Applied Energy, Elsevier, vol. 384(C).
    5. Ye, Lin & Peng, Yishu & Li, Yilin & Li, Zhuo, 2024. "A novel informer-time-series generative adversarial networks for day-ahead scenario generation of wind power," Applied Energy, Elsevier, vol. 364(C).
    6. Liu, Xin & Yu, Jingjia & Gong, Lin & Liu, Minxia & Xiang, Xi, 2024. "A GCN-based adaptive generative adversarial network model for short-term wind speed scenario prediction," Energy, Elsevier, vol. 294(C).
    7. Donglin Li & Xiaoxin Zhao & Weimao Xu & Chao Ge & Chunzheng Li, 2025. "A Novel Renewable Energy Scenario Generation Method Based on Multi-Resolution Denoising Diffusion Probabilistic Models," Energies, MDPI, vol. 18(14), pages 1-22, July.
    8. Dong, Xiaochong & Sun, Yingyun & Yang, Yue & Mao, Zhihang, 2025. "Controllable renewable energy scenario generation based on pattern-guided diffusion models," Applied Energy, Elsevier, vol. 398(C).
    9. Zhao, Wei & Shao, Zhen & Yang, Shanlin & Lu, Xinhui, 2025. "A novel conditional diffusion model for joint source-load scenario generation considering both diversity and controllability," Applied Energy, Elsevier, vol. 377(PC).
    Full references (including those not matched with items on IDEAS)

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Hu, Jinxing & Cao, Yimai & Tan, Guoqiang, 2025. "A dynamic spatiotemporal graph generative adversarial network for scenario generation of renewable energy with nonlinear dependence," Energy, Elsevier, vol. 335(C).
    2. Zhang, Xuanyu & Wang, Jun & Wang, Yunuo & Gao, Kaize & Yu, Zeguang & Cheng, Tian & Jin, Shaohua & Yu, Xingchuan & Wang, Yonggang, 2025. "MS-CGDM: Multi-scale conditional graph diffusion model for extreme weather source-load scenario generation," Energy, Elsevier, vol. 336(C).
    3. Feng, Zhong-kai & Wang, Xin & Niu, Wen-jing & Li, Jian-bing & Zhang, Jun & Bai, Tao, 2026. "Two-stage scenario generation of hydro-wind-solar complementary system based on improved variational autoencoder and generative adversarial networks model," Renewable Energy, Elsevier, vol. 262(C).
    4. Xie, Yujie & Li, Zhengrong & Jiang, Fujian & Tao, Ruiyang & Zhu, Han, 2026. "A diffusion-based generative framework for multi-energy scenario modeling in low-carbon building clusters," Energy, Elsevier, vol. 344(C).
    5. Donglin Li & Xiaoxin Zhao & Weimao Xu & Chao Ge & Chunzheng Li, 2025. "A Novel Renewable Energy Scenario Generation Method Based on Multi-Resolution Denoising Diffusion Probabilistic Models," Energies, MDPI, vol. 18(14), pages 1-22, July.
    6. Feng, Zhong-kai & Wang, Xin & Niu, Wen-jing, 2025. "Complementary operation optimization of cascade hydropower reservoirs and photovoltaic energy using cooperation search algorithm and conditional generative adversarial networks," Energy, Elsevier, vol. 328(C).
    7. Iqra Nazir & Nermish Mushtaq & Waqas Amin, 2025. "Smart Grid Systems: Addressing Privacy Threats, Security Vulnerabilities, and Demand–Supply Balance (A Review)," Energies, MDPI, vol. 18(19), pages 1-77, September.
    8. Yan, Jie & Li, Xiuyu & Wang, Han & Si, Fangyuan & Qiao, Wenjie & Liu, Yongqian, 2025. "The economic value of wind power forecasting: a data-driven method and its application in various scenarios," Energy, Elsevier, vol. 340(C).
    9. Yan, Ke & Bi, Jian & Wang, Hua & Gao, Yuan & Afshari, Afshin, 2025. "A stable, reliable and interpretable diffusion model for HVAC FDD with data unavailability," Applied Energy, Elsevier, vol. 401(PC).
    10. Lihua Zhong & Feng Pan & Yuyao Yang & Lei Feng & Haiming Shao & Jiafu Wang, 2025. "Nodal Carbon Emission Factor Prediction for Power Systems Based on MDBO-CNN-LSTM," Energies, MDPI, vol. 18(13), pages 1-28, July.
    11. Song, Weiye & Yan, Jie & Han, Shuang & Liu, Shihua & Wang, Han & Dai, Qiangsheng & Huo, Xuesong & Liu, Yongqian, 2024. "A multi-task spatio-temporal fusion network for offshore wind power ramp events forecasting," Renewable Energy, Elsevier, vol. 237(PB).
    12. Bohórquez Correa, Santiago & Mosquera-López, Stephanía & Uribe, Jorge M., 2026. "Time-varying systemic risk in electricity markets using generative adversarial networks: Market resilience and policy," Energy Policy, Elsevier, vol. 210(C).
    13. Xie, Yujie & Xiong, Wenda & Zhang, Shuzheng & Li, Zhengrong & Johnson, Brian C. & Zhu, Han, 2026. "Deep learning-based distributionally robust optimization scheduling in the low carbon park integrated energy system under multiple uncertainties," Energy, Elsevier, vol. 344(C).
    14. M. G. Sukharev & I. V. Tverskoy & G. A. Suraev, 2026. "Theory and Practice of Gas Consumption Forecasting in Planning the Development of Regional Gas Supply Systems," Studies on Russian Economic Development, Springer, vol. 37(2), pages 246-256, April.
    15. Wang, Gong & Dong, Ke & Song, Yuanhua & Cao, Shengxian & Duan, Jie & Duan, Guichao & Wu, Dan & Li, Shaofan, 2025. "Optimal battery storage capacity planning model and DOD regulation strategy for islanded microgrid based on distributed generation and a microturbine," Energy, Elsevier, vol. 332(C).
    16. Liang Ma & Shigong Jiang & Yi Song & Chenyi Si & Xiaohan Li, 2025. "Multi-Time Scale Scenario Generation for Source–Load Modeling Through Temporal Generative Adversarial Networks," Energies, MDPI, vol. 18(6), pages 1-18, March.
    17. Andrea Scrocca & Roberto Pisani & Diego Andreotti & Giuliano Rancilio & Maurizio Delfanti & Filippo Bovera, 2025. "Optimal Spot Market Participation of PV + BESS: Impact of BESS Sizing in Utility-Scale and Distributed Configurations," Energies, MDPI, vol. 18(14), pages 1-32, July.
    18. Liuqing Gu & Jian Xu & Deping Ke & Youhan Deng & Xiaojun Hua & Yi Yu, 2024. "Short-Term Output Scenario Generation of Renewable Energy Using Transformer–Wasserstein Generative Adversarial Nets-Gradient Penalty," Sustainability, MDPI, vol. 16(24), pages 1-20, December.
    19. Jie Zhang & Xinchun Zhu & Yigong Xie & Guo Chen & Shuangquan Liu, 2025. "Detection and Prediction of Wind and Solar Photovoltaic Power Ramp Events Based on Data-Driven Methods: A Critical Review," Energies, MDPI, vol. 18(13), pages 1-20, June.
    20. Liu, Zixuan & Mo, Li & Zhang, Mi & Kang, Jiangrui & Liu, Wan & Sun, Xutong & Xiao, Wenjing, 2025. "High-dimensional scenario generation method joint-driven by multiple correlations for hydro-wind-photovoltaic," Applied Energy, Elsevier, vol. 400(C).

    More about this item

    Keywords

    ;
    ;
    ;
    ;
    ;

    Statistics

    Access and download statistics

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:eee:appene:v:409:y:2026:i:c:s0306261926001248. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: Catherine Liu (email available below). General contact details of provider: http://www.elsevier.com/wps/find/journaldescription.cws_home/405891/description#description .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.