| 2 | 0 | 3 |
| 下载次数 | 被引频次 | 阅读次数 |
针对配电网量测设备部署不全、数据传输丢失等导致的量测数据稀疏问题，提出一种基于GINN（图填补神经网络）的配电网稀疏量测数据推演方法，以解决配电网现有量测数据精度低、稀疏度高的问题。首先，基于GINN的量测特征编码器模块，提取配电网节点量测数据的功率、电压等潮流特征，并利用Transformer网络建立了节点量测不同潮流特征之间的关联。其次，基于GINN的图编码器模块，建立了配电网节点间的拓扑连接关系，并利用GCN（图卷积网络）实现了节点量测潮流特征的传递与更新。然后，通过两个模块分别捕捉的节点量测数据不同潮流特征间的关系和节点间的拓扑关联，利用稀疏的量测数据实现了缺失数据的推演补齐。最后，采用IEEE 14、30、57和118节点系统开展仿真测试，验证了所提方法的有效性。
Abstract：Incomplete deployment of measurement devices and data transmission losses can result in sparse measurements in distribution networks. To address this issue, this paper proposes an inference method for sparse measurements based on a graph imputation neural network(GINN). The proposed method aims to improve the accuracy and reduce the sparsity of existing measurements. First, a GINN-based measurement feature encoder module is designed to extract power flow features such as power and voltage from nodal measurements. A transformer network is employed to model cross-feature correlations among different power flow features. Second, a GINN-based graph encoder module explicitly encodes topological connectivity between distribution network nodes. By incorporating a graph convolutional network(GCN), this module enables the propagation and updating of nodal power flow features. Subsequently, by leveraging two modules to capture the correlations between different power flow features of node measurements and the topological correlations across nodes, the missing data is inferred and completed using the sparse measurements. Finally, simulation tests are conducted on IEEE 14-, 30-, 57-, and 118-bus systems to validate the effectiveness of the proposed method.
[1]NAYAK S,DWIVEDI D,BABU K V S M,et al.Data imputation using self attention based model for enhancing distribution grid monitoring and protection systems[J].IEEE Transactions on Instrumentation and Measurement,2024,73:1-11.
[2]SHAHBAZIAN R,GRECO S.Generative adversarial networks assist missing data imputation:a comprehensive survey and evaluation[J]. IEEE Access,2023,11:88908-88928.
[3]张新鹤，何桂雄，梁琛，等.基于分割区域的配电网异常线损数据辨识与修正[J].浙江电力，2023,42(10):90-100.ZHANG Xinhe,HE Guixiong,LIANG Chen,et al.Identification and correction of abnormal line loss data in distribution networks based on segmented regions[J].Zhejiang Electric Power,2023,42(10):90-100.
[4]张汪洋，樊艳芳，侯俊杰，等.基于集成深度神经网络的配电网分布式状态估计方法[J].电力系统保护与控制，2024,52(3):128-140.ZHANG Wangyang,FAN Yanfang,HOU Junjie,et al.Distribution network distributed state estimation method based on an integrated deep neural network[J].Power System Protection and Control,2024,52(3):128-140.
[5]LEI C,BU S Q,WANG Q G,et al.Observability defenseconstrained distribution network reconfiguration for cyberphysical security enhancement[J]. IEEE Transactions on Smart Grid,2024,15(2):2379-2382.
[6]LI Y Y,SONG L D,HU Y,et al.Load profile inpainting for missing load data restoration and baseline estimation[J].IEEE Transactions on Smart Grid,2024,15(2):2251-2260.
[7]吴莉艳，孙开元，陈坤，等.基于CNN-LSSVM的电力系统虚假数据攻击检测[J].浙江电力，2024,43(11):90-96.WU Liyan,SUN Kaiyuan,CHEN Kun,et al.Detection of false data injection attacks against power systems using a CNN-LSSVM model[J].Zhejiang Electric Power,2024,43(11):90-96.
[8]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.
[9]HABIB B,ISUFI E,VAN BREDA W,et al.Deep Statistical Solver for Distribution System State Estimation[J].IEEE Transactions on Power Systems,2024,39(2):4039-4050.
[10]赵洪山，寿佩瑶，马利波.低压台区缺失数据的张量补全方法[J].中国电机工程学报，2020,40(22):7328-7337.ZHAO Hongshan,SHOU Peiyao,MA Libo. A tensor completion method of missing data in transformer district[J].Proceedings of the CSEE,2020,40(22):7328-7337.
[11]APRILLIA H,YANG H T,HUANG C-M. Statistical load forecasting using optimal quantile regression random forest and risk assessment index[J].IEEE Transactions on Smart Grid,2021,12(2):1467-1480.
[12]WANG Y,WANG Y Q,SUN Y H,et al. Resilient dynamic state estimation for multi-machine power system with partial missing measurements[J].IEEE Transactions on Power Systems,2024,39(2):3299-3309.
[13]XU D L,XU J J,QIAN C,et al.A pseudo-measurement modelling strategy for active distribution networks considering uncertainty of DGs[J]. Protection and Control of Modern Power Systems,2024,9(5):1-15.
[14]赵友国，刘尚伟，王冠中，等.基于正交分解的电力系统状态估计可观性分析[J].浙江电力，2021,40(7):1-5.ZHAO Youguo,LIU Shangwei,WANG Guanzhong,et al.Observability analysis of power system state estimation based on orthogonal decomposition[J]. Zhejiang Electric Power,2021,40(7):1-5.
[15]WANG Y J,GU J,YUAN L.Distribution network state estimation based on attention-enhanced recurrent neural network pseudo-measurement modeling[J].Protection and Control of Modern Power Systems,2023,8:31.
[16]王守相，陈海文，潘志新，等.采用改进生成式对抗网络的电力系统量测缺失数据重建方法[J].中国电机工程学报，2019,39(1):56-64.WANG Shouxiang,CHEN Haiwen,PAN Zhixin,et al.A reconstruction method for missing data in power system measurement using an improved generative adversarial network[J].Proceedings of the CSEE,2019,39(1):56-64.
[17]王子馨，胡俊杰，刘宝柱.基于长短期记忆网络的电力系统量测缺失数据恢复方法[J].电力建设，2021,42(5):1-8.WANG Zixin,HU Junjie,LIU Baozhu.Recovery method for missing measurement data of power systems based on long short-term memory networks[J].Electric Power Construction,2021,42(5):1-8.
[18]俞文帅，张晓华，卫志农，等.基于深度神经网络的电力系统快速状态估计[J].电网技术，2021,45(7):2551-2561.YU Wenshuai,ZHANG Xiaohua,WEI Zhinong,et al.Fast state estimation for power system based on deep neural network[J].Power System Technology,2021,45(7):2551-2561.
[19]杨隽雯，尚磊，叶欣智，等.考虑配电网故障重构的电压薄弱节点辨识方法[J].电力工程技术，2025,44(1):39-49.YANG Juanwen,SHANG Lei,YE Xinzhi,et al.A voltage weak node identification method considering fault reconstruction in distribution networks[J].Jiangsu Electrical Engineering,2025,44(1):39-49
[20]呼士召，刘仕琦，江健健，等.配电网多负荷场景下移动储能两阶段经济运行策略[J].智慧电力，2025,53(1):45-53.HU Shizhao,LIU Shiqi,JIANG Jianjian,et al. A twostage economic operation strategy for mobile energy storage considering different load scenarios in distribution network[J].Smart Power,2025,53(1):45-53.
[21]蔡木良，范瑞祥，贺贵东，等.基于时间规律聚合电动汽车的有源配电网源荷储协同调控[J].智慧电力，2025,53(1):54-61.CAI Muliang,FAN Ruixiang,HE Guidong,et al.Sourceload-storage coordinated scheduling for active distribution network based on aggregation of electric vehicles with time pattern[J].Smart Power,2025, 53(1):54-61.
[22]许超，李永刚，张书伟，等.考虑配电网三相电压特征的IHPO-CSSVM电压暂降源识别[J].电力需求侧管理，2025,27(1):101-106.XU Chao,LI Yonggang,ZHANG Shuwei,et al.Voltage sag source identification using IHPO-CSSVM with consideration of three-phase voltage characteristics on the distribution network[J]. Power Demand Side Management,2025,27(1):101-106.
[23]张祥龙，袁兆祥，董树锋，等.考虑节点碳排放强度的输配协同多目标最优潮流[J].电力建设，2025,46(7):123-132.ZHANG Xianglong,YUAN Zhaoxiang,DONG Shufeng,et al. Multi-objective optimal power flow of integrated transmission and distribution network considering node carbon emission intensity[J].Electric Power Construction,2025,46(7):123-132.
[24]陈彬，廖锦霖.极端天气下多灾害地区配电网防灾能力提升技术综述及展望[J].电力建设，2025,46(1):107-121.CHEN Bin,LIAO Jinlin.Technology for improving distribution network disaster-prevention capabilities for intercurrent natural disasters areas under extreme weather:review and prospect[J]. Electric Power Construction,2025,46(1):107-121.
基本信息:
DOI：10.19585/j.zjdl.202603009
中图分类号:TM73;TP183
引用信息:
[1]李企洲,李梁,赵健,等.基于图填补神经网络的配电网稀疏量测数据推演方法[J].浙江电力,2026,45(03):96-105.DOI:10.19585/j.zjdl.202603009.
基金信息:
国家自然科学基金(51907114)