Typical wind‑PV scenario generation based on improved CGAN‑ARIMA hybrid model

LI Xiaoyang; CAO Yongji; LI Changgang; LI Na; YI Yanlin; LI Baoliang

doi:10.19783/j.cnki.pspc.260095

English Version Journal Login

您当前的位置：

首页 >

文章列表页 >

Typical wind‑PV scenario generation based on improved CGAN‑ARIMA hybrid model

更新时间：2026-10-16

- Typical wind‑PV scenario generation based on improved CGAN‑ARIMA hybrid model
- Power System Protection and Control Vol. 54, Issue 17, (2026)
- 作者机构：
- 作者简介：
- 基金信息：
- DOI：10.19783/j.cnki.pspc.260095
  CLC：
- Published：2026
- 稿件说明：
移动端阅览
LI Xiaoyang, CAO Yongji, LI Changgang, et al. Typical wind‑PV scenario generation based on improved CGAN‑ARIMA hybrid model[J]. Power System Protection and Control, 2026, 54(17).
DOI：

LI Xiaoyang, CAO Yongji, LI Changgang, et al. Typical wind‑PV scenario generation based on improved CGAN‑ARIMA hybrid model[J]. Power System Protection and Control, 2026, 54(17). DOI： 10.19783/j.cnki.pspc.260095.

摘要

在可再生能源高比例接入的背景下，电力系统面临不确定性的复杂程度加深，导致运行与规划愈发依赖精细化的场景生成。针对单一深度生成模型可解释性不足且难以保证物理可行性的问题，结合深度生成模型的隐式学习能力与参数统计模型的显式建模能力，提出基于改进条件生成对抗网络 (conditional generative adversarial network

CGAN) 和自回归积分滑动平均 (autoregressive integrated moving average

ARIMA) 组合模型的风光典型场景生成方法。首先，利用 ARIMA 模型对出力数据中的低频趋势分量进行建模，并提取高频残差序列。其次，构建内嵌长短期记忆网络的改进 CGAN，并通过在生成器损失函数中引入统计正则项，改善生成残差的分布特性，从而实现高频残差序列建模。然后，基于核主成分分析和高斯混合模型，对生成的高维场景矩阵进行非线性降维、自适应聚类和概率加权，以提取具有概率权重的典型场景。最后，算例分析结果表明，所提方法能够降低 50% 以上的 Wasserstein 距离和 40% 以上的条件风险价值误差，验证了其有效性。

Abstract

With the high penetration of renewable energy

the complexity of uncertainties faced by power systems has intensified

making operational planning increasingly reliant on refined scenario generation. To address the issues of insufficient interpretability and difficulty in ensuring physical feasibility in a single deep generative model

a typical wind and PV output scenario generation method based on an improved conditional generative adversarial network (CGAN) and autoregressive integrated moving average (ARIMA) hybrid model is proposed

which integrates the implicit learning capability of deep generative models with the explicit modeling capability of parametric statistical models. First

the ARIMA model is used to capture the low‑frequency trend components of the output data

while extracting the high‑frequency residual sequences. Then

an improved CGAN model integrated with long short‑term memory network is constructed. A statistical regularization term is introduced into the generator loss function to refine the distribution characteristics of residuals

thereby achieving high‑frequency residual sequence modeling. Moreover

kernel principal component analysis and a Gaussian mixture model are applied to perform nonlinear dimensionality reduction

adaptive clustering

and probability weighting on the generated high‑dimensional scenario matrices

thereby extracting typical scenarios with probability weights. Finally

case studies indicate that the proposed approach reduces the Wasserstein distance index by more than 50% and the conditional value‑at‑risk error by over 40%

confirming its effectiveness.

关键词

Keywords

references

LIU Lijun, HU Xin, CHEN Junsheng, et al. Embedded scenario clustering for wind and photovoltaic power, and load based on multi‑head self‑attention[J]. Protection and Control of Modern Power Systems, 2024, 9(1): 122-132.

PAPAEFTHYMIOU G, KLOCKL B. MCMC for wind power simulation[J]. IEEE Transactions on Energy Conversion, 2008, 23(1): 234-240.

MORALES J M, MINGUEZ R, CONEJO A J. A methodology to generate statistically dependent wind speed scenarios[J]. Applied Energy, 2010, 87(3): 843-855.

LI Z, PENG X, CUI W, et al. A novel scenario generation method of renewable energy using improved VAEGAN with controllable interpretable features[J]. Applied Energy, 2024, 363.

DONG X, SUN Y, YANG Y, et al. Controllable renewable energy scenario generation based on pattern‑guided diffusion models[J]. Applied Energy, 2025, 398.

YUAN R, WANG B, SUN Y, et al. Conditional style‑ based generative adversarial networks for renewable scenario generation[J]. IEEE Transactions on Power Systems, 2023, 38(2): 1281-1296.

ZHAO W, SHAO Z, YANG S, et al. A novel conditional diffusion model for joint source‑load scenario generation considering both diversity and controllability[J]. Applied Energy, 2025, 377.

WANG H, QIN B, HONG S, et al. Enhanced GAN based joint wind‑solar‑load scenario generation with extreme weather labelling[J]. IEEE Transactions on Smart Grid, 2025, 16(5): 4213-4224.

DONG W, CHEN X, YANG Q. Data‑driven scenario generation of renewable energy production based on controllable generative adversarial networks with interpretability[J]. Applied Energy, 2022, 308.

HUANG B, WANG J. Applications of physics‑informed neural networks in power systems‑a review[J]. IEEE Transactions on Power Systems, 2023, 38(1): 572-588.

LI J, ZHOU J, CHEN B. Review of wind power scenario generation methods for optimal operation of renewable energy systems[J]. Applied Energy, 2020, 280.

CHO Y, ZHU H, IM J, et al. Wind power scenario generation based on the generalized dynamic factor model and generative adversarial network[J]. IEEE Transactions on Power Systems, 2026, 41(2): 1135-1147.

WANG Q, ZHANG J, HU J, et al. A CGAN‑based adversarial attack method for data‑driven state estimation[J]. International Journal of Electrical Power Energy Systems, 2025, 170.

BU X, WU Q, ZHOU B, et al. Hybrid short‑term load forecasting using CGAN with CNN and semi‑supervised regression[J]. Applied Energy, 2023, 338.

YOON J, JARRETT D, VAN DER SCHAAR M. Time‑ series generative adversarial networks[C] // Advances in Neural Information Processing Systems, December 8‑14, 2019, Vancouver, Canada: 5508‑5518.

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

考虑光伏不确定性的主动配电网自适应鲁棒优化经济调度策略

基于自适应高斯混合模型的含高渗透率分布式光伏电力系统风险评估

考虑预测误差不确定性和功率互济的配电网直流合环重构

基于改进MMD-GAN的可再生能源随机场景生成

基于特征提取与INGO-SVM的变压器故障诊断方法

Related Author

SONG Ziwei

XIE Biao

LIU Hongda

WANG Zhenyu

LU Fang

LIAO Jiaqi

Related Institution

Yantai Research Institute of Harbin Engineering University

SONG Ziwei(1. College of Intelligent Science and Engineering, Harbin Engineering University

State Grid Shandong Electric Power Company

XU Xiaohui(1. China Electric Power Research Institute

Construction Branch, State Grid Jilin Electric Power Company Limited

AI问答

⁰