朱耿,蒋元元,王波,贺旭,王晴
ZHU Geng,JIANG Yuanyuan,WANG Bo,HE Xu,WANG Qing

• 1:国网浙江省电力有限公司宁波供电公司
• 2:宁波市电力设计院有限公司

摘要(Abstract)：

光伏场站量测数据的匮乏以及传感器故障、通信中断等造成的数据缺失，将影响功率预测的准确性与鲁棒性。因此，以构建统一多源域筛选机制与数据增强框架为目标，提出一种基于Voronoi图与改进TT-GAN（变换器生成对抗网络）的光伏时序数据增强方法。基于Voronoi图与数据强度指标实现多场景下迁移学习源站点集的动态选取，构建迁移学习赋能的Transformer-GAN模型，改进模型优化处理结构与微调方法，基于自注意力机制与有监督训练增强其处理数据噪声与特征学习的能力，使其适应数据生成和数据修补的不同目标。实验结果表明，所提模型在现有光伏时序数据集基础上实现了数据质量提升，能够提高功率预测的准确性。
The scarcity of measured data from photovoltaic(PV) power stations and data gaps caused by sensor failures or communication interruptions significantly compromise the accuracy and robustness of power forecasting. To address these challenges, this paper proposes a novel data enhancement method for PV time-series data based on Voronoi diagram and transfer learning-enabled transformer-based generative adversarial network(TT-GAN). The method aims to establish a unified mechanism for multi-source domain selection and data enhancement framework. A Voronoi diagram combined with a data-strength metric is used to dynamically select source station sets under diverse scenarios. Subsequently, a TT-GAN model is developed, incorporating structural and fine-tuning optimizations. Enhanced with a self-attention mechanism and supervised training, the model improves its ability to handle data noise and feature representation learning, making it suitable for both data generation and data repair tasks. Experimental results demonstrate that the proposed model significantly improves data quality on existing PV timeseries datasets and enhances the accuracy of power forecasting.

关键词(KeyWords)： 数据增强;Voronoi图;数据强度;迁移学习;变换器生成对抗网络
data enhancement;Voronoi diagram;data strength;transfer learning;GAN

Abstract:

Keywords:

基金项目(Foundation): 宁波永耀电力投资集团有限公司科技项目（KJCX009）

作者(Author): 朱耿,蒋元元,王波,贺旭,王晴
ZHU Geng,JIANG Yuanyuan,WANG Bo,HE Xu,WANG Qing

DOI: 10.19585/j.zjdl.202601010

参考文献(References)：

• [1]周孝信，赵强，张玉琼，等.“双碳”目标下我国能源电力系统发展趋势分析：绿电替代与绿氢替代[J].中国电机工程学报，2024,44(17):6707-6721.ZHOU Xiaoxin,ZHAO Qiang,ZHANG Yuqiong,et al.Analysis of the development trend of China’s energy and power system under the dual carbon target:green electricity substitution and green hydrogen substitution[J]. Proceedings of the CSEE,2024,44(17):6707-6721.
• [2]胡厚鹏，刘伟，肖艳红，等.基于调度容量影响的并网光伏与V2G运行多目标优化[J].电力工程技术，2025,44(6):123-133.HU Houpeng,LIU Wei,XIAO Yanhong,et al. Multiobjective optimization of grid connected photovoltaics and V2G operation based on the influence of schedulable capacity[J].Electric Power Engineering Technology,2025,44(6):123-133.
• [3]文贤馗，周科，张俊玮，等.基于单端口降阶模型的分布式光伏接入配电网交互影响分析[J].电力工程技术，2025,44(4):187-196.WEN Xiankui,ZHOU Ke,ZHANG Junwei,et al.Interaction effect analysis of distributed photovoltaic access to distributed network based on single-port reduced model[J].Electric Power Engineering Technology,2025,44(4):187-196.
• [4]邹启衡，李洁，钱科军，等.用于光伏发电的新型双极性输出DC-DC变换器[J].电测与仪表，2025,62(4):217-224.ZOU Qiheng,LI Jie,QIAN Kejun,et al.Novel bipolar output DC-DC converter for photovoltaic generation[J].Electrical Measurement&Instrumentation,2025,62(4):217-224.
• [5]水恒华，顾阳，徐晓春，等.一种适用于光伏高渗透率地区的太阳辐照短时预测技术研究[J].电测与仪表，2024,61(4):149-154.SHUI Henghua,GU Yang,XU Xiaochun,et al.Research on a short-term solar radiation prediction technology for photovoltaic high permeability area[J].Electrical Measurement&Instrumentation,2024,61(4):149-154.
• [6]许涛，王国春，董昱，等.新型电力系统平衡机理及演进过程研究[J].中国电机工程学报，2025,45(1):1-14.XU Tao,WANG Guochun,DONG Yu,et al.Research on power balance mechanism and evolution of new power system[J].Proceedings of the CSEE,2025,45(1):1-14.
• [7]张思，杨晓雷，阙凌燕，等.高比例光伏发电对浙江电网电力平衡的影响及应对策略[J].浙江电力，2022,41(11):9-16.ZHANG Si,YANG Xiaolei,QUE Lingyan,et al.The impact of high-proportion photovoltaic power generation on the power balance of Zhejiang power grid and its countermeasures[J].Zhejiang Electric Power,2022,41(11):9-16.
• [8]郑之轩，倪妮，吴思媛.计及光伏消纳和需求响应的典型农业园区调度优化[J].电力需求侧管理，2025,27(5):30-35.ZHENG Zhixuan,NI Ni,WU Siyuan.Optimal dispatch of typical agricultural park considering photovoltaic consumption and demand response[J].Power Demand Side Management,2025,27(5):30-35.
• [9]李黄强，赵发金，舒征宇，等.考虑多种调控手段的分布式光伏承载能力提升优化模型[J].电力需求侧管理，2025,27(2):82-87.LI Huangqiang,ZHAO Fajin,SHU Zhengyu,et al. Enhancement optimization model for distributed photovoltaic hosting capacity considering multiple adjustment methods[J]. Power Demand Side Management,2025,27(2):82-87.
• [10]姜建国，金方承，毕洪波.多策略改进蜣螂优化算法及其在光伏发电功率预测中的应用[J].电力需求侧管理，2024,26(6):101-106.JIANG Jianguo,JIN Fangcheng,BI Hongbo. Multistrategy improved dung beetle optimization algorithm and its application in photovoltaic power generation power prediction[J]. Power Demand Side Management,2024,26(6):101-106.
• [11]董昱，孙大雁，许丹，等.新型电力系统电力电量平衡的挑战、应对与展望[J].中国电机工程学报，2025,45(6):2039-2057.DONG Yu,SUN Dayan,XU Dan,et al. Challenges,response and prospects for power balance in new power systems[J]. Proceedings of the CSEE,2025,45(6):2039-2057.
• [12]朱琼锋，李家腾，乔骥，等.人工智能技术在新能源功率预测的应用及展望[J].中国电机工程学报，2023,43(8):3027-3048.ZHU Qiongfeng,LI Jiateng,QIAO Ji,et al. Application and prospect of artificial intelligence technology in renewable energy forecasting[J]. Proceedings of the CSEE,2023,43(8):3027-3048.
• [13]王小君，窦嘉铭，刘曌，等.可解释人工智能在电力系统中的应用综述与展望[J].电力系统自动化，2024,48(4):169-191.WANG Xiaojun,DOU Jiaming,LIU Zhao,et al.Review and prospect of explainable artificial intelligence and its application in power systems[J]. Automation of Electric Power Systems,2024,48(4):169-191.
• [14]孙秋野，张瑞霞，陈东岳.大模型技术赋能电力系统的应用及技术路线展望[J/OL].电力系统自动化，2025:1-22.(2025-03-18)[2025-04-02].https：//kns.cnki.net/KCMS/detail/detail. aspx?filename=DLXT20250317003&dbname=CJFD&dbcode=CJFQ.SUN Qiuye,ZHANG Ruixia,CHEN Dongyue. Application and technical route prospect of large model technology to empower power system[J/OL]. China Industrial Economics,2025:1-22.(2025-03-18)[2025-04-02].https：//kns. cnki. net/KCMS/detail/detail. aspx? filename=DLXT20250317003&dbname=CJFD&dbcode=CJFQ.
• [15]贺兴，潘美琪，艾芊.小样本学习技术在新型电力系统中的应用与挑战[J].电力系统自动化，2024,48(6):74-82.HE Xing,PAN Meiqi,AI Qian. Applications and challenges of few-shot learning technologies in new power system[J].Automation of Electric Power Systems,2024,48(6):74-82.
• [16]王晓霞，艾兴成，王涛.基于实例迁移学习的小样本光伏功率短期预测[J].太阳能学报，2024,45(6):325-333.WANG Xiaoxia,AI Xingcheng,WANG Tao. Few-shot photovoltaic power short-term forecasting based on instance transfer learning[J].Acta Energiae Solaris Sinica,2024,45(6):325-333.
• [17]郑珂，王丽婕，郝颖，等.基于数据集蒸馏的光伏发电功率超短期预测[J].中国电机工程学报，2024,44(13):5196-5208.ZHENG Ke,WANG Lijie,HAO Ying,et al.Ultra-shortterm prediction of photovoltaic power based on dataset distillation[J].Proceedings of the CSEE,2024,44(13):5196-5208.
• [18]彭维锋，董树锋，邱剑.基于特征约束与目标驱动的WGAN-GP光伏特定多场景生成方法[J/OL].中国电机工程学报，2025:1-15.(2025-04-17)[2025-04-27].https：//kns. cnki. net/kcms/detail/11.2107. tm. 20250416.1528.016.html.PENG Weifeng,DONG Shufeng,QIU Jian. WGAN-GP photovoltaic specific multi-scene generation method based on feature constraints and target driving[J/OL].Proceedings of the CSEE,2025:1-15.(2025-04-17)[2025-04-27].https：//kns.cnki.net/kcms/detail/11.2107.tm.20250416.1528.016.html.
• [19]孟凡斌，南钰，武亚非，等.基于谱归一化生成对抗网络与谱聚类的典型风力发电场景生成[J].浙江电力，2024,43(12):86-94.MENG Fanbin,NAN Yu,WU Yafei,et al.Generation of typical wind power scenarios based on spectral normalization generative adversarial networks and spectral clustering[J].Zhejiang Electric Power,2024,43(12):86-94.
• [20]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):987-1004.SHAO Zhenguo,ZHANG Chengsheng,CHEN Feixiong,et al. A review on generative adversarial networks for power system applications[J].Proceedings of the CSEE,2023,43(3):987-1004.
• [21]任佳星，孙英云，秦继朔，等.基于改进域对抗网络的新能源基地风光时序功率曲线生成方法[J].电网技术，2024,48(8):3409-3417.REN Jiaxing,SUN Yingyun,QIN Jishuo,et al.Improved domain adversarial neural networks based generation method of wind-photovoltaic power time series curves for renewable energy base[J]. Power System Technology,2024,48(8):3409-3417.
• [22]HU Z D,LI Y B,HAN C. Transfer learning enabled transformer-based generative adversarial networks for modeling and generating terahertz channels[J].Communications Engineering,2024,3:153.
• [23]顾菊平，赵佳皓，张新松，等.电力设备多参量监测数据清洗研究现状及展望[J].高电压技术，2024,50(8):3403-3420.GU Juping,ZHAO Jiahao,ZHANG Xinsong,et al. Research review and prospect of data cleaning for multiparameter monitoring data of power equipment[J]. High Voltage Engineering,2024,50(8):3403-3420.
• [24]裘愉涛，张磊，周开运，等.基于图像特征检测的光伏异常数据识别算法[J].浙江电力，2025,44(5):42-52.QIU Yutao,ZHANG Lei,ZHOU Kaiyun,et al.A photovoltaic anomaly data identification method based on image feature detection[J]. Zhejiang Electric Power,2025,44(5):42-52.
• [25]周嘉琪，毕利.基于GAN的光伏逆变器数据异常检测技术[J].电力系统保护与控制，2022,50(1):133-140.ZHOU Jiaqi,BI Li.Abnormal detection technology of photovoltaic inverter data based on GAN[J]. Power System Protection and Control,2022,50(1):133-140.
• [26]周远翔，林孟龙，陈健宁，等.基于自注意力生成对抗网络的电力设备在线监测缺失数据填补[J].高电压技术，2023,49(5):1795-1809.ZHOU Yuanxiang,LIN Menglong,CHEN Jianning,et al.Missing data imputation for online monitoring of power equipment based on self-attention generative adversarial networks[J]. High Voltage Engineering,2023,49(5):1795-1809.
• [27]回茜，刘俊宇，刘鑫，等.含分布式光伏的新型电力系统负荷数据特征增强方法[J].太阳能学报，2025,46(4):240-247.HUI Qian,LIU Junyu,LIU Xin,et al.New power system load data feature enhancement method with distributed photovoltaics[J]. Acta Energiae Solaris Sinica,2025,46(4):240-247.
• [28]ALLIEZ P,COHEN-STEINER D,TONG Y Y,et al.Voronoi-based variational reconstruction of unoriented point sets[J].Symposium on Geometry Processing,2007,67(5):39-48.
• [29]SHEWCHUK J R.Delaunay refinement algorithms for triangular mesh generation[J]. Computational Geometry,2002,22(1/2/3):21-74.
• [30]XU J,LI Z S,DU B W,et al.Reluplex made more practical:leaky ReLU[C]//2020 IEEE Symposium on Computers and Communications(ISCC). July 7-10,2020.Rennes,France.IEEE,2020:1-7.
• [31]张赟宁，魏广军.考虑特征选择的短期光伏功率组合预测模型[J].电力系统及其自动化学报，2024,36(8):122-132.ZHANG Yunning,WEI Guangjun. Combined prediction model for short-term photovoltaic power considering feature selection[J].Proceedings of the CSU-EPSA,2024,36(8):122-132.
• [32]王德文，焦天媛.基于二次分解的不同太阳辐射下光伏功率预测[J].太阳能学报，2024,45(9):360-368.WANG Dewen,JIAO Tianyuan. Prediction of photovoltaic power under different solar radiation based on secondary decomposition[J].Acta Energiae Solaris Sinica,2024,45(9):360-368.