A Two-Stage Generative Architecture for Renewable Scenario Generation Based on Temporal Scenario Representation and Diffusion Models

Chenglong Xu, Peidong Xu, Yuxin Dai, Shi Su, Luxi Zhang, Jun Zhang (), Yuyang Bai, Tianlu Gao, Qingyang Xie, Lei Shang and Wenzhong Gao
Additional contact information
Chenglong Xu: School of Electrical Engineering and Automation, Wuhan University, Wuhan 430072, China
Peidong Xu: School of Electrical Engineering and Automation, Wuhan University, Wuhan 430072, China
Yuxin Dai: School of Electrical Engineering and Automation, Wuhan University, Wuhan 430072, China
Shi Su: Electric Power Research Institute of Yunnan Power Grid Co., Ltd., Kunming 650217, China
Luxi Zhang: Physics Department, Brandeis University, Waltham, MA 02453, USA
Jun Zhang: School of Electrical Engineering and Automation, Wuhan University, Wuhan 430072, China
Yuyang Bai: School of Electrical Engineering and Automation, Wuhan University, Wuhan 430072, China
Tianlu Gao: School of Electrical Engineering and Automation, Wuhan University, Wuhan 430072, China
Qingyang Xie: Electric Power Research Institute of Yunnan Power Grid Co., Ltd., Kunming 650217, China
Lei Shang: School of Electrical Engineering and Automation, Wuhan University, Wuhan 430072, China
Wenzhong Gao: Department of Electrical and Computer Engineering, University of Denver, Denver, CO 80208, USA

Energies, 2025, vol. 18, issue 5, 1-21

Abstract: Scenario generation proves to be an effective approach for addressing uncertainties in stochastic programming for power systems with integrated renewable resources. In recent years, numerous studies have explored the application of deep generative models to scenario generation. Considering the challenge of characterizing renewable resource uncertainty, in this paper, we propose a novel two-stage generative architecture for renewable scenario generation using diffusion models. Specifically, in the first stage the temporal features of the renewable energy output are learned and encoded into the hidden space by means of a representational model with an encoder–decoder structure, which provides the inductive bias of the scenario for generation. In the second stage, the real distribution of vectors in the hidden space is learned based on the conditional diffusion model, and the generated scenario is obtained through decoder mapping. The case study demonstrates the effectiveness of this architecture in generating high-quality renewable scenarios. In comparison to advanced deep generative models, the proposed method exhibits superior performance in a comprehensive evaluation.

Keywords: renewable resource; generative model; diffusion models; scenario generation; scenario representation (search for similar items in EconPapers)
JEL-codes: Q Q0 Q4 Q40 Q41 Q42 Q43 Q47 Q48 Q49 (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/1996-1073/18/5/1275/pdf (application/pdf)
https://www.mdpi.com/1996-1073/18/5/1275/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jeners:v:18:y:2025:i:5:p:1275-:d:1606033

Access Statistics for this article

Energies is currently edited by Ms. Agatha Cao

More articles in Energies from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().