1.兰州交通大学 自动化与电气工程学院,甘肃 兰州 730070
2.国网甘肃省电力公司经济技术研究院(新型电力系统研究院),甘肃 兰州 730050
高锋阳(1970 —),男,教授,博士研究生导师,主要研究方向为电力系统优化运行及配电网运行规划(E-mail:ljdgaofy@ lzjtu.edu.cn);
裴淑萍(2000 —),女,硕士研究生,主要研究方向为电力系统优化调度(E-mail:pshuping_2000@163.com)。
收稿:2025-03-19,
修回:2025-08-11,
网络首发:2025-08-15,
纸质出版:2026-05-10
移动端阅览
高锋阳,裴淑萍,李龙等.基于改进生成对抗网络的可控可解释性风光场景生成方法[J].电力自动化设备,2026,46(05):118-126.
Gao Fengyang,Pei Shuping,Li Long,et al.Controllable and interpretable wind-solar scenario generation method based on improved generative adversarial network[J].Electric Power Automation Equipment,2026,46(05):118-126.
高锋阳,裴淑萍,李龙等.基于改进生成对抗网络的可控可解释性风光场景生成方法[J].电力自动化设备,2026,46(05):118-126. DOI: 10.16081/j.epae.202508010.
Gao Fengyang,Pei Shuping,Li Long,et al.Controllable and interpretable wind-solar scenario generation method based on improved generative adversarial network[J].Electric Power Automation Equipment,2026,46(05):118-126. DOI: 10.16081/j.epae.202508010.
针对风光可再生能源接入电网所带来的不确定性和间歇性,提出一种基于条件Wasserstein生成对抗网络-梯度惩罚(cWGAN-GP)的可控可解释的风光出力场景生成方法。cWGAN-GP通过引入条件向量调控风光出力场景的生成过程,使生成数据能够满足特定统计特征要求,结合梯度惩罚提升训练稳定性,确保生成场景质量,并准确捕捉风光出力的时空相关性;利用斯皮尔曼相关系数分析高维气象特征与风光出力之间的关系,筛选关键气象因子作为控制变量,以增强模型的可控性和对气象条件的适应能力。在IEEE 33节点系统上进行仿真验证,结果表明,所提方法能有效生成符合统计规律的风光出力场景,并较好地保持时空相关性。
Aiming at the uncertainty and intermittency brought by the integration of wind and solar rene-wable energy into power grid,a controllable and interpretable wind-solar output scenario generation method based on the conditional Wasserstein generative adversarial network with gradient penalty(cWGAN-GP) is proposed. The generation process of wind-solar output scenarios is regulated by introducing conditional vectors in cWGAN-GP,which ensures that the generated data meets specific statistical characteristics requirement. The gradient penalty is incorporated to enhance the training stability,which ensures the quality of generated scenarios while accurately capturing the spatiotemporal correlation of wind-solar output. The Spearman correlation coefficient is employed to analyze the relationship between high dimensional meteorological features and wind-solar output,and key meteorological factors are selected as the control variables to improve the model controllability and its adaptability to meteorological conditions. The IEEE 33-bus system is used for simulation and verification,and the results show that the proposed method can effectively generate wind-solar output scenarios conforming to statistical rules,and maintain spatiotemporal correlation well.
顾光荣 , 杨鹏 , 汤波 , 等 . 源-荷-储协同优化的配电网平衡能力提升方法 [J]. 中国电机工程学报 , 2024 , 44 ( 13 ): 5097 - 5108 .
Gu Guangrong , Yang Peng , Tang Bo , et al . A method for improving the balance ability of distribution networks through source-load-storage collaborative optimization [J]. Proceedings of the CSEE , 2024 , 44 ( 13 ): 5097 - 5108 .
杨续松 , 罗先觉 , 王建学 , 等 . 含大规模可再生能源的电力系统中长期时序-随机生产模拟方法 [J]. 电力自动化设备 , 2026-02-10 . https:∥doi.org/10.16081/j.epae.202602011 https://doi.org/10.16081/j.epae.202602011 .
李夫刚 , 李夫海 , 琚承乾 , 等 . 新能源不确定性表征方法及关键技术问题研究现状、挑战及展望 [J]. 电力系统保护与控制 , 2025 , 53 ( 15 ): 172 - 187 .
Li Fugang , Li Fuhai , Ju Chengqian , et al . Methods for characterizing renewable energy uncertainty and key technical issues:research status,challenges,and prospects [J]. Power System Protection and Control , 2025 , 53 ( 15 ): 172 - 187 .
兰健 , 郭庆来 , 周艳真 , 等 . 基于生成对抗网络和模型迁移的电力系统典型运行方式样本生成 [J]. 中国电机工程学报 , 2022 , 42 ( 8 ): 2889 - 2899 .
Lan Jian , Guo Qinglai , Zhou Yanzhen , et al . Generation of po-wer system typical operation mode samples:a generation adversarial network and model-based transfer learning approach [J]. Proceedings of the CSEE , 2022 , 42 ( 8 ): 2889 - 2899 .
殷佳敏 , 谢宁 , 王承民 , 等 . 基于分形理论的新型电力系统规划场景生成方法 [J]. 电力自动化设备 , 2024 , 44 ( 7 ): 94 - 100,188 .
Yin Jiamin , Xie Ning , Wang Chengmin , et al . Generation method of planning scenario for new power system based on fractal theory [J]. Electric Power Automation Equipment , 2024 , 44 ( 7 ): 94 - 100,188 .
邹金 , 卢斯煜 , 卓映君 , 等 . 基于多场景时序运行模拟的电力电量平衡评估方法 [J]. 电力系统自动化 , 2025 , 49 ( 23 ): 139 - 148 .
Zou Jin , Lu Siyu , Zhuo Yingjun , et al . Evaluation method of electric power and energy balance based on multi-scenario time-series operation simulation [J]. Automation of Electric Power Systems , 2025 , 49 ( 23 ): 139 - 148 .
葛彦硕 , 周艳真 , 兰健 , 等 . 电力电量平衡视角下基于LSTM-ACGAN的特定风电时序场景生成 [J]. 电力自动化设备 , 2025 , 45 ( 11 ): 10 - 16,24 .
Ge Yanshuo , Zhou Yanzhen , Lan Jian , et al . Specific wind power sequential scenario generation based on LSTM-ACGAN from perspective of electric power and energy balance [J]. Electric Power Automation Equipment , 2025 , 45 ( 11 ): 10 - 16,24 .
Aliabadi M J , Radmehr M . Optimization of hybrid renewable energy system in radial distribution networks considering uncer-tainty using meta-heuristic crow search algorithm [J]. Applied Soft Computing , 2021 , 107 : 107384 .
Song Y , Liu T , Hill D J . Chance constrained economic dispatch considering the capability of network flexibility against rene-wable uncertainties [J]. IEEE Transactions on Power Systems , 2024 , 39 ( 5 ): 6636 - 6648 .
Liu Z H , Liu S L , Li Q H , et al . Optimal day-ahead schedu-ling of islanded microgrid considering risk-based reserve deci-sion [J]. Journal of Modern Power Systems and Clean Energy , 2021 , 9 ( 5 ): 1149 - 1160 .
牟长兴 , 张俊涛 , 程春田 , 等 . 考虑时空相关性的流域水风光多能互补系统高维不确定性场景生成方法 [J]. 电网技术 , 2024 , 48 ( 9 ): 3614 - 3623 .
Mu Changxing , Zhang Juntao , Cheng Chuntian , et al . High-dimensional uncertainty scenario generation method for hydro-wind-solar multi-energy complementary system considering spatio-temporal correlation [J]. Power System Technology , 2024 , 48 ( 9 ): 3614 - 3623 .
Vagropoulos S I , Kardakos E G , Simoglou C K , et al . ANN-based scenario generation methodology for stochastic variables of electric power systems [J]. Electric Power Systems Research , 2016 , 134 : 9 - 18 .
吴艳梅 , 陈红坤 , 陈磊 , 等 . 基于改进MMD-GAN的可再生能源随机场景生成 [J]. 电力系统保护与控制 , 2024 , 52 ( 19 ): 85 - 96 .
Wu Yanmei , Chen Hongkun , Chen Lei , et al . Stochastic scenario generation for renewable energy based on improved MMD-GAN [J]. Power System Protection and Control , 2024 , 52 ( 19 ): 85 - 96 .
陈浩 , 张文朝 , 黄志光 , 等 . 考虑极端天气的先验知识引导风/光短期出力场景生成方法研究 [J]. 智慧电力 , 2025 , 53 ( 3 ): 44 - 52 .
Chen Hao , Zhang Wenchao , Huang Zhiguang , et al . Research on prior knowledge-guided short-term wind/photovoltaic output scenario generation method considering extreme weather [J]. Smart Power , 2025 , 53 ( 3 ): 44 - 52 .
王成磊 , 匡熠 , 濮永现 , 等 . 基于改进生成对抗网络场景生成的长-短期储能优化配置 [J]. 高电压技术 , 2024 , 50 ( 3 ): 1131 - 1144 .
Wang Chenglei , Kuang Yi , Pu Yongxian , et al . Optimal configuration of long-term and short-term energy storage based on improved generative adversarial network scenarios [J]. High Voltage Engineering , 2024 , 50 ( 3 ): 1131 - 1144 .
Wang Y B , Liu Y X , Yang Q . Operational scenario generation and forecasting for integrated energy systems [J]. IEEE Tran-sactions on Industrial Informatics , 2024 , 20 ( 2 ): 2920 - 2931 .
陈志威 , 吴毓峰 , 潘振宁 , 等 . 基于图表示学习和特征引导的电力系统运行场景生成方法 [J]. 中国电机工程学报 , 2024 , 44 ( 24 ): 9521 - 9532 .
Chen Zhiwei , Wu Yufeng , Pan Zhenning , et al . A power system operating scenario generation method based on graph representation learning and feature guidance [J]. Proceedings of the CSEE , 2024 , 44 ( 24 ): 9521 - 9532 .
张帅 , 刘文霞 , 万海洋 , 等 . 基于改进条件生成对抗网络的可控场景生成方法 [J]. 电力自动化设备 , 2024 , 44 ( 6 ): 9 - 17 .
Zhang Shuai , Liu Wenxia , Wan Haiyang , et al . Controllable scenario generation method based on improved conditional generative adversarial network [J]. Electric Power Automation Equipment , 2024 , 44 ( 6 ): 9 - 17 .
黄越辉 , 孙亚南 , 李驰 , 等 . 基于条件生成对抗网络的多区域风电短期出力场景生成方法 [J]. 电网技术 , 2023 , 47 ( 1 ): 63 - 72 .
Huang Yuehui , Sun Yanan , Li Chi , et al . Constructing method of short-term output scenarios for multi-regional wind power based on conditional generative adversarial network [J]. Power System Technology , 2023 , 47 ( 1 ): 63 - 72 .
Tan Y H , Zhang Q , Shi L , et al . A novel short-term wind power scenario generation method combining multiple algori-thms for data-missing wind farm Considering spatial-temporal correlativity [J]. International Journal of Electrical Power & Energy Systems , 2024 , 162 : 110227 .
Dong W , Chen X Q , Yang Q . Data-driven scenario generation of renewable energy production based on controllable generative adversarial networks with interpretability [J]. Applied Energy , 2022 , 308 : 118387 .
罗萍萍 , 盛奥 , 林济铿 , 等 . 基于可解释性条件生成对抗网络的台风气象负荷场景生成方法 [J]. 电力系统自动化 , 2025 , 49 ( 2 ): 186 - 197 .
Luo Pingping , Sheng Ao , Lin Jikeng , et al . Scenario generation method of typhoon meteorological load based on interpretability conditional generative adversarial network [J]. Automation of Electric Power Systems , 2025 , 49 ( 2 ): 186 - 197 .
Li Z L , Peng X G , Cui W B , et al . A novel scenario gene-ration method of renewable energy using improved VAEGAN with controllable interpretable features [J]. Applied Energy , 2024 , 363 : 122905 .
陈凡 , 陈刘明 , 王曼 , 等 . 基于改进信息最大化生成对抗网络的风光出力场景可控生成方法 [J]. 电网技术 , 2024 , 48 ( 4 ): 1477 - 1486 .
Chen Fan , Chen Liuming , Wang Man , et al . Controllable scena-rio generation method for wind power and photovoltaic output based on improved InfoGAN [J]. Power System Technology , 2024 , 48 ( 4 ): 1477 - 1486 .
Wang Q , Zhang X G , Xu D G . Source-load scenario generation based on weakly supervised adversarial learning and its data-driven application in energy storage capacity sizing [J]. IEEE Transactions on Sustainable Energy , 2023 , 14 ( 4 ): 1918 - 1932 .
邵振国 , 张承圣 , 陈飞雄 , 等 . 生成对抗网络及其在电力系统中的应用综述 [J]. 中国电机工程学报 , 2023 , 43 ( 3 ): 987 - 1003 .
Shao Zhenguo , Zhang Chengsheng , Chen Feixiong , et al . A review on generative adversarial networks for power system app-lications [J]. Proceedings of the CSEE , 2023 , 43 ( 3 ): 987 - 1003 .
米阳 , 周杰 , 卢长坤 , 等 . 基于改进生成对抗网络与碳足迹的配电网多目标双层规划 [J]. 中国电机工程学报 , 2024 , 44 ( 21 ): 8421 - 8434 .
Mi Yang , Zhou Jie , Lu Changkun , et al . A multi-objective bi-level planning of distribution network based on improved gene-rative adversarial network and carbon footprint [J]. Procee-dings of the CSEE , 2024 , 44 ( 21 ): 8421 - 8434 .
Li Y , Cao J T , Xu Y , et al . Deep learning based on Transfor-mer architecture for power system short-term voltage stability assessment with class imbalance [J]. Renewable and Sustai-nable Energy Reviews , 2024 , 189 : 113913 .
Ye S M , Wang H , Tan M K , et al . Recurrent affine transfor-mation for text-to-image synthesis [J]. IEEE Transactions on Multimedia , 2024 , 26 : 462 - 473 .
李辉 , 任洲洋 , 胡博 , 等 . 基于时序生成对抗网络的月度风光发电功率场景分析方法 [J]. 中国电机工程学报 , 2022 , 42 ( 2 ): 537 - 547 .
Li Hui , Ren Zhouyang , Hu Bo , et al . A sequential generative adversarial network based monthly scenario analysis method for wind and photovoltaic power [J]. Proceedings of the CSEE , 2022 , 42 ( 2 ): 537 - 547 .
0
浏览量
0
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构
京公网安备11010802024621