基于不完全量测数据的配电网状态估计方法

doi:10.11930/j.issn.1004-9649.202407002

摘要/Abstract

摘要：

随着分布式能源的大规模接入，传统配电网的运行特性发生显著变化，导致负荷分散、实时可观性差和数据不完整等问题，严重影响了配电网的状态监测和运行优化。对此，提出了一种基于不完全实时量测数据的贝叶斯优化卷积神经网络（convolutional neural networks，CNN）与长短期记忆网络（long short-term memory，LSTM）结合的配电网状态估计方法。该方法分为离线学习和在线状态估计2个阶段。离线学习部分，利用生成对抗网络生成所需样本，以训练CNN-LSTM模型，并采用贝叶斯优化算法调整超参数，从而提升算法的准确性。在线状态估计部分，基于不完全的配电网实时数据和训练完成的CNN-LSTM模型进行在线状态估计。最后，算例基于IEEE 33和IEEE 123网络进行仿真分析，验证了所提状态估计方法的有效性和准确性。

关键词: 配电网, 状态估计, 不完全量测, 卷积神经网络, 长短期记忆网络, 贝叶斯优化

Abstract:

With the large-scale integration of distributed energy resources, the operational characteristics of the traditional distribution networks have undergone significant changes, leading to such problems as dispersed loads, poor real-time observability, and incomplete data, which severely impact the state monitoring and operational optimization of the distribution networks. To address above problems, we propose a distribution network state estimation method based on Bayesian-optimized convolutional neural networks (CNN) and long short-term memory (LSTM) networks with incomplete real-time measurement data. The method is divided into two phases: offline learning and online state estimation. In the offline learning phase, generative adversarial networks are used to generate the required samples for training the CNN-LSTM model, and the Bayesian optimization algorithm is employed to adjust the hyperparameters, thereby enhancing the accuracy of the algorithm. In the online state estimation phase, the state estimation is performed online with incomplete real-time data of the distribution network and the trained CNN-LSTM model. Finally, simulation analysis is conducted on the IEEE 33 and IEEE 123 networks, which confirms the effectiveness and accuracy of the proposed state estimation method.

Key words: distribution network, state estimation, incomplete measurement, convolutional neural networks, long short-term memory, Bayesian optimization

李鹏, 祖文静, 刘一欣, 田春筝, 郝元钊, 李慧璇. 基于不完全量测数据的配电网状态估计方法[J]. 中国电力, 2025, 58(5): 1-10.

LI Peng, ZU Wenjing, LIU Yixin, TIAN Chunzheng, HAO Yuanzhao, LI Huixuan. State Estimation Method for Distribution Network Based on Incomplete Measurement Data[J]. Electric Power, 2025, 58(5): 1-10.

导出引用管理器 EndNote|Ris|BibTeX

链接本文: https://www.electricpower.com.cn/CN/10.11930/j.issn.1004-9649.202407002

https://www.electricpower.com.cn/CN/Y2025/V58/I5/1

图/表 15

图 1 总体建模思路

Fig.1 Overall modeling approach

图 2 卷积神经网络结构

Fig.2 Convolutional neural networks structure

图 3 CNN-LSTM组合模型结构

Fig.3 CNN-LSTM combined model structure

图 4 基于贝叶斯优化的CNN-LSTM模型优化流程

Fig.4 CNN-LSTM model optimization process based on Bayesian optimization

图 5 IEEE 33节点配电网测量配置

Fig.5 Measurement configuration of the IEEE 33-node distribution network

表 1 Adam参数设置

Table 1 Adam parameter settings

参数		数值
β₁		0.9
β₂		0.999
η		e^–8

图 6 各节点电压幅值状态估计结果

Fig.6 State estimation results of the voltage magnitude at each node

图 7 各节点电压相角状态估计结果

Fig.7 State estimation results of the voltage phase angle at each node

图 8 不同断面下节点2电压幅值和相角绝对误差

Fig.8 Absolute error of the voltage magnitude and phase angle at node 2 across different sections

图 9 4种预测模型电压幅值MAE的比较分析

Fig.9 Comparative analysis of the MAE for voltage magnitude across four prediction models

图 10 4种预测模型电压相角MAE的比较分析

Fig.10 Comparative analysis of the MAE for voltage phase angle across four prediction models

表 2 节点5电压幅值和相角MAE的比较分析

Table 2 Comparative analysis of the MAE for voltage magnitude and phase angle at node 5

算法	电压幅值MAE (10^–3 p.u.)	电压相角MAE (10^–3 p.u.)	状态估计时间/s
WLS	1.28	2.25	0.46
本文方法	0.59	1.16	0.41

图 11 IEEE 123节点配电网测量配置

Fig.11 Measurement configuration of the IEEE 123-node distribution network

图 12 各节点电压幅值和相角的MAE

Fig.12 The MAE of the voltage magnitude and phase angle at each node

表 3 不同测量噪声下节点9电压幅值和相角的MAE

Table 3 The MAE of the voltage magnitude and phase angle at node 9 with different measurement noise

测量噪声/%	电压幅值MAE(10^–3 p.u.)	电压相角MAE(10^–3 p.u.)
1	1.05	1.35
2	1.28	1.67
3	1.42	2.26

参考文献 25

1	陈子靖, 蒋金琦, 赵健, 等. 基于CNN-AE-MAML的低压配电网自适应分类方法[J]. 电力建设, 2024, 45 (5): 48- 58.
	CHEN Zijing, JIANG Jinqi, ZHAO Jian, et al. Adaptive classification method of low voltage distribution network based on CNN-AE-MAML[J]. Electric Power Construction, 2024, 45 (5): 48- 58.
2	陈维江, 靳晓凌, 吴鸣, 等. 双碳目标下我国配电网形态快速演进的思考[J]. 中国电机工程学报, 2024, 44 (17): 6811- 6818.
	CHEN Weijiang, JIN Xiaoling, WU Ming, et al. Thinking on the rapid evolution of distribution network form under the carbon peaking and carbon neutrality goals[J]. Proceedings of the CSEE, 2024, 44 (17): 6811- 6818.
3	葛磊蛟, 李元良, 陈艳波, 等. 智能配电网态势感知关键技术及实施效果评价[J]. 高电压技术, 2021, 47 (7): 2269- 2280.
	GE Leijiao, LI Yuanliang, CHEN Yanbo, et al. Key technologies of situation awareness and implementation effectiveness evaluation in smart distribution network[J]. High Voltage Engineering, 2021, 47 (7): 2269- 2280.
4	何振武, 姜飞, 欧阳卫, 等. 基于自适应分区和SFVMD-LSTM伪量测建模的新型配电系统抗差状态估计[J]. 电力建设, 2024, 45 (10): 78- 89. DOI
	HE Zhenwu, JIANG Fei, OUYANG Wei, et al. Novel distribution system robust state estimation based on adaptive partitioning and SFVMD-LSTM pseudo-measurement modeling[J]. Electric Power Construction, 2024, 45 (10): 78- 89. DOI
5	刘辉, 杨坤, 王枭枭, 等. 基于ADMM算法的中低压配电网多目标分布式协调优化运行策略[J]. 电力建设, 2024, 45 (9): 100- 112.
	LIU Hui, YANG Kun, WANG Xiaoxiao, et al. Multi-objective distributed optimal scheduling of distribution network with high-permeability distributed photovoltaic resource access[J]. Electric Power Construction, 2024, 45 (9): 100- 112.
6	罗玉春, 王毅, 闪鑫, 等. KLU稀疏直接求解器在状态估计中的应用[J]. 中国电力, 2019, 52 (2): 111- 118.
	LUO Yuchun, WANG Yi, SHAN Xin, et al. Application of KLU sparse direct linear solver in state estimation[J]. Electric Power, 2019, 52 (2): 111- 118.
7	李诗伟, 骆晨, 何叶, 等. 多源量测环境下计及时延融合的配电网区间状态估计[J]. 电力系统自动化, 2024, 48 (12): 120- 129. DOI
	LI Shiwei, LUO Chen, HE Ye, et al. Interval state estimation for distribution network considering time-delay fusion in multi-source measurement environment[J]. Automation of Electric Power Systems, 2024, 48 (12): 120- 129. DOI
8	田钧祥, 陈铁, 陈彬. 基于改进自适应UKF算法的中压配电网鲁棒动态状态估计方法[J]. 中国电力, 2023, 56 (11): 128- 133.
	TIAN Junxiang, CHEN Tie, CHEN Bin. Robust dynamic state estimation method for medium voltage distribution networks based on improved adaptive UKF algorithm[J]. Electric Power, 2023, 56 (11): 128- 133.
9	龚成明, 於益军, 路轶, 等. 加权最小二乘状态估计量测权值计算的实用方法[J]. 电力系统自动化, 2016, 40 (11): 143- 147. DOI
	GONG Chengming, YU Yijun, LU Yi, et al. Practical method for calculating measurement weights in weighted least square state estimation[J]. Automation of Electric Power Systems, 2016, 40 (11): 143- 147. DOI
10	朱鹏程, 柳劲松, 范士雄, 等. 考虑混合量测的配电网二次约束二次估计方法[J]. 电网技术, 2019, 43 (3): 841- 847.
	ZHU Pengcheng, LIU Jinsong, FAN Shixiong, et al. A quadratic constraint quadratic estimation method based on hybrid measurements for distribution networks[J]. Power System Technology, 2019, 43 (3): 841- 847.
11	马鑫, 郭瑞鹏, 柳劲松, 等. 三相不平衡下交直流配电网状态估计[J]. 电力系统自动化, 2019, 43 (23): 65- 71. DOI
	MA Xin, GUO Ruipeng, LIU Jinsong, et al. State estimation for three-phase unbalanced AC/DC distribution network[J]. Automation of Electric Power Systems, 2019, 43 (23): 65- 71. DOI
12	张占龙, 马海涛, 施伟成, 等. 一种能适应弱环网的改进配电网支路电流状态估计算法[J]. 中国电力, 2015, 48 (8): 61- 66.
	ZHANG Zhanlong, MA Haitao, SHI Weicheng, et al. A revised branch-current-based state estimation method for weak looped distribution network[J]. Electric Power, 2015, 48 (8): 61- 66.
13	YILMAZ U C, ABUR A. A robust parallel distributed state estimation for large scale distribution systems[J]. IEEE Transactions on Power Systems, 2024, 39 (2): 4437- 4445. DOI
14	孙国强, 殷岩岩, 卫志农, 等. 基于深度确定性策略梯度的主动配电网有功-无功协调优化调度[J]. 电力建设, 2023, 44 (11): 33- 42.
	SUN Guoqiang, YIN Yanyan, WEI Zhinong, et al. Coordinated optimal dispatch of active and reactive power in active distribution networks using deep deterministic strategy gradient[J]. Electric Power Construction, 2023, 44 (11): 33- 42.
15	齐韵英, 许潇, 殷科, 等. 基于深度强化学习的含储能有源配电网电压联合调控技术[J]. 电力建设, 2023, 44 (11): 64- 74.
	QI Yunying, XU Xiao, YIN Ke, et al. Voltage co-regulation technology of active distribution network with energy storage based on deep reinforcement learning[J]. Electric Power Construction, 2023, 44 (11): 64- 74.
16	高岩, 吴汉斌, 张纪欣, 等. 基于组合深度学习的光伏功率日前概率预测模型[J]. 中国电力, 2024, 57 (4): 100- 110.
	GAO Yan, WU Hanbin, ZHANG Jixin, et al. Day-ahead probabilistic prediction model for photovoltaic power based on combined deep learning[J]. Electric Power, 2024, 57 (4): 100- 110.
17	AHMAD F, TARIQ M, FAROOQ A. A novel ANN-based distribution network state estimator[J]. International Journal of Electrical Power & Energy Systems, 2019, 107, 200- 212.
18	TRAN M Q, ZAMZAM A S, NGUYEN P H, et al. Multi-area distribution system state estimation using decentralized physics-aware neural networks[J]. Energies, 2021, 14 (11): 3025. DOI
19	兰浦哲, 韩冬, 徐潇源, 等. 基于长短期记忆的电-气耦合综合能源系统贝叶斯状态估计[J]. 电力系统自动化, 2021, 45 (20): 18- 28. DOI
	LAN Puzhe, HAN Dong, XU Xiaoyuan, et al. Bayesian state estimation for electricity-gas coupled integrated energy system based on long short-term memory[J]. Automation of Electric Power Systems, 2021, 45 (20): 18- 28. DOI
20	刘晓莉, 曾祥晖, 黄翊阳, 等. 联合粒子滤波和卷积神经网络的电力系统状态估计方法[J]. 电网技术, 2020, 44 (9): 3361- 3367.
	LIU Xiaoli, ZENG Xianghui, HUANG Yiyang, et al. State estimation based on particle filtering and convolutional neural networks for power systems[J]. Power System Technology, 2020, 44 (9): 3361- 3367.
21	夏添梁, 张玉敏, 杨明, 等. 联合长短期记忆神经网络和粒子滤波的配电网预测辅助鲁棒状态估计方法[J]. 高电压技术, 2022, 48 (4): 1343- 1355.
	XIA Tianliang, ZHANG Yumin, YANG Ming, et al. Robust forecasting-aided state estimation method of distribution network based on long-short term memory neural network and particle filter[J]. High Voltage Engineering, 2022, 48 (4): 1343- 1355.
22	梁栋, 刘啸宇, 曾林, 等. 基于潮流引导神经网络的配电网贝叶斯状态估计[J]. 高电压技术, 2024, 50 (11): 4864- 4874.
	LIANG Dong, LIU Xiaoyu, ZENG Lin, et al. Bayesian state estimation for distribution networks based on power flow-informed neural networks[J]. High Voltage Engineering, 2024, 50 (11): 4864- 4874.
23	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, 320.
	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, 320.
24	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.
25	SINGH P, CHAUDHURY S, PANIGRAHI B K. Hybrid MPSO-CNN: multi-level particle swarm optimized hyperparameters of convolutional neural network[J]. Swarm and Evolutionary Computation, 2021, 63, 100863. DOI

[1]	沈鑫, 王钢, 赵毅涛, 骆钊, 李钊, 杨晓华. 融合SENet注意力机制和GA-CNN的非侵入式负荷识别方法[J]. 中国电力, 2025, 58(5): 33-42.
[2]	汪进锋, 李金鹏, 许银亮, 刘海涛, 何锦雄, 许建远. 考虑不确定性和绿证交易的虚拟电厂与配电网分布式优化[J]. 中国电力, 2025, 58(4): 21-30, 192.
[3]	徐慧慧, 田云飞, 赵宇洋, 彭婧, 石庆鑫, 成锐. 基于条件生成对抗网络与多智能体强化学习的配电网可靠性评估方法[J]. 中国电力, 2025, 58(4): 230-236.
[4]	贺春光, 王林峰, 曹媛, 安佳坤, 雷子健, 宋关羽, 冀浩然. 考虑综合收益的多电压等级配电网柔性互联装置协同规划方法[J]. 中国电力, 2025, 58(1): 78-84.
[5]	陶磊, 罗萍萍, 林济铿. 基于深度学习的直流微电网虚假数据注入攻击二阶段检测方法[J]. 中国电力, 2024, 57(9): 11-19.
[6]	贺全鹏, 刘苇, 杨维永, 魏兴慎, 王琦. 针对负荷重分配攻击的移动目标防御策略[J]. 中国电力, 2024, 57(9): 44-52.
[7]	张玉敏, 张涌琛, 叶平峰, 吉兴全, 石春友, 蔡富东, 李一宸. 基于集合经验模态分解的增强核岭回归配电系统状态估计[J]. 中国电力, 2024, 57(9): 156-168.
[8]	祝士焱, 许寅, 和敬涵, 王颖. 基于多微电网投影的配电系统协调恢复方法[J]. 中国电力, 2024, 57(9): 224-230.
[9]	张亚健, 陈茨, 薛飞, 马丽, 郑敏. 电制氢协同的含高比例光伏配电网两阶段电压随机优化控制[J]. 中国电力, 2024, 57(8): 23-35.
[10]	孙东磊, 孙毅, 刘蕊, 孙鹏凯, 张玉敏. 计及多层级配电网的分布式新能源最大消纳空间分解测算[J]. 中国电力, 2024, 57(8): 108-116.
[11]	凡鹏飞, 李宝琴, 侯江伟, 李嵘, 宋崇明, 林凯骏. 配电网分布式电源经济可承载力评估[J]. 中国电力, 2024, 57(7): 196-202.
[12]	王家武, 赵佃云, 刘长锋, 陈康, 张玉敏. 基于目标级联法的多主体主动配电网自治协同优化[J]. 中国电力, 2024, 57(7): 214-226.
[13]	朱沐雨, 马宏忠, 郭鹏宇, 宣文婧. 典型调峰/调频工况下储能电池组荷电状态估计[J]. 中国电力, 2024, 57(6): 18-26.
[14]	韩璟琳, 胡平, 侯若松, 陈志永, 李洪涛, 柴园园. 计及多光储一体机的配电网电压优化控制策略[J]. 中国电力, 2024, 57(6): 69-77, 152.
[15]	徐峰亮, 王克谦, 王文豪, 王鹏, 王文烨, 张帅, 赵凤展. 计及激励型需求响应的低压配电网混合储能优化配置[J]. 中国电力, 2024, 57(6): 90-101.