基于深度神经网络伪量测建模的交直流混合配电网交替迭代法状态估计

doi:10.12204/j.issn.1000-7229.2022.10.011

电力建设 ›› 2022, Vol. 43 ›› Issue (10): 111-120.doi: 10.12204/j.issn.1000-7229.2022.10.011

基于深度神经网络伪量测建模的交直流混合配电网交替迭代法状态估计

龚逊东¹(), 费有蝶²(), 凌佳凯¹(), 胡金峰¹(), 秦军¹(), 卫志农²(), 臧海祥²()

1.国网江苏省电力有限公司无锡供电分公司,江苏省无锡市 214061
2.河海大学能源与电气学院,南京市 211100

收稿日期:2022-03-23 出版日期:2022-10-01 发布日期:2022-09-29
通讯作者: 费有蝶 E-mail:gxd@js.sgcc.com.cn;2286520005@qq.com;lingjiakaiwuxi@163.com;thorpe_113@qq.com;ben_qinjun@125.com;wzn_nj@263.net;zanghaixiang@hhu.edu.cn
作者简介:龚逊东(1971),男,硕士,高级工程师,主要从事电力调度工作,E-mail: gxd@js.sgcc.com.cn;
凌佳凯(1978),男,本科,高级技师,主要从事电力安全管理、一流配电网规划工作,E-mail: lingjiakaiwuxi@163.com;
胡金峰(1985),男,本科,高级工程师,主要从事电力系统规划与调度工作,E-mail: thorpe_113@qq.com;
秦军(1977),男,硕士,高级工程师,主要从事电网运维检修管理工作,E-mail: ben_qinjun@125.com;
卫志农(1962),男,博士,教授,博士生导师,主要研究方向为电力系统运行分析与控制、输配电系统自动化,E-mail: wzn_nj@263.net;
臧海祥(1986),男,博士,副教授,博士生导师,主要研究方向为电力系统规划与运行分析、人工智能在电力系统中的应用,E-mail: zanghaixiang@hhu.edu.cn。
基金资助:
国网江苏省电力有限公司科技项目(J2021026);国家自然科学基金资助项目(U1966205)

Alternating-Iteration State Estimation of AC/DC Hybrid Distribution System Based on Pseudo-Measurement Modeling Using Deep Neural Network

GONG Xundong¹(), FEI Youdie²(), LING Jiakai¹(), HU Jinfeng¹(), QIN Jun¹(), WEI Zhinong²(), ZANG Haixiang²()

1. Wuxi Power Supply Company of State Grid Jiangsu Electric Power Co., Ltd., Wuxi 214061, Jiangsu Province, China
2. College of Energy and Electrical Engineering, Hohai University, Nanjing 211100, China

Received:2022-03-23 Online:2022-10-01 Published:2022-09-29
Contact: FEI Youdie E-mail:gxd@js.sgcc.com.cn;2286520005@qq.com;lingjiakaiwuxi@163.com;thorpe_113@qq.com;ben_qinjun@125.com;wzn_nj@263.net;zanghaixiang@hhu.edu.cn
Supported by:
State Grid Jiangsu Electric Power Co., Ltd. Research Program(J2021026);National Natural Science Foundation of China(U1966205)

摘要/Abstract

摘要：

当前配电网状态估计面临的一个突出问题是实时量测数量不足,难以实现全网可观性。为了给配电管理系统提供准确的基础数据,提出一种基于深度神经网络伪量测建模的交直流混合配电网交替迭代状态估计方法。首先,建立电压源换流器的稳态模型和混合配电网的实时量测模型;然后,利用历史量测数据对深度神经网络进行离线训练,建立负荷节点注入功率的伪量测模型;最后,对交流区域和直流区域进行交替迭代状态估计,在交替过程中区域间交换VSC支路状态量的估计值,保证了边界状态量的一致性。算例测试结果表明,所提方法能在实时量测覆盖率低的情况下,准确估计混合配电网的状态值。

关键词: 混合配电网, 交替迭代状态估计, 深度神经网络, 伪量测

Abstract:

At present, a prominent problem in the state estimation of distribution system is the lack of real-time measurements, which makes it difficult to realize the observability of the whole network. In order to provide accurate basic data for distribution management system (DMS), an alternating-iteration state estimation method based on pseudo measurement modeling using deep neural networks (DNN) is proposed. Firstly, the steady-state model of voltage source converter (VSC) and the real-time measurement model of hybrid distribution system are presented. Then the historical measurements are used to train DNN off-line and establish pseudo-measurement models of power injection on load buses. Finally, alternating-iteration state estimation is carried out for AC and DC areas. Only the estimated states of VSC branches need to be exchanged, thus ensuring the consistency of the boundary states. Test results show that the proposed method can accurately estimate the states of hybrid distribution system under low coverage of real-time measurements.

Key words: hybrid distribution system, alternating-iteration state estimation, deep neural network, pseudo measurement

中图分类号:

TM74

龚逊东, 费有蝶, 凌佳凯, 胡金峰, 秦军, 卫志农, 臧海祥. 基于深度神经网络伪量测建模的交直流混合配电网交替迭代法状态估计[J]. 电力建设, 2022, 43(10): 111-120.

GONG Xundong, FEI Youdie, LING Jiakai, HU Jinfeng, QIN Jun, WEI Zhinong, ZANG Haixiang. Alternating-Iteration State Estimation of AC/DC Hybrid Distribution System Based on Pseudo-Measurement Modeling Using Deep Neural Network[J]. ELECTRIC POWER CONSTRUCTION, 2022, 43(10): 111-120.

图/表 16

图1 VSC等效模型

Fig.1 Equivalent model of VSC

图2 DNN伪量测模型训练图

Fig.2 Training of DNN-based pseudo-measurement model

图3 混合配电网分区示意图

Fig.3 Sub-area of hybrid distribution network

图4 本文算法流程图

Fig.4 Flow chart of the proposed method

表1 测试集的误差

Table 1 Error of the test set

图5 DNN输出对比

Fig.5 Comparison of DNN outputs

图6 不同伪量测集下CSE和AISE的最大估计误差

Fig.6 Maximum estimation error of state variables obtained by CSE and AISE with different pseudo measurement sets

图7 AISE dnn的收敛曲线

Fig.7 Convergence of the AISE dnn

表2 VSC支路变量的平均估计误差

Table 2 Mean estimation error of VSC branch variables

表3 计算时间统计结果

Table 3 Statistical results of calculating time

图A1 混合配电网测试系统一

Fig.A1 Test system 1 of hybrid distribution network

图A2 混合配电网测试系统二

Fig.A2 Test system 2 of hybrid distribution network

表A1 系统一中VSC的参数及控制方式

Table A1 Model parameters and control modes of VSC in system 1

表A2 系统一的实时量测配置

Table A2 Real measurement configuration of system 1

表A3 系统二中VSC的参数及控制方式

Table A3 Model parameters and control modes of VSC in system 2

表A4 系统二的实时量测配置

Table A4 Real measurement configuration of system 2

参考文献 29

[1]	卞艺衡, 桂恒立, 别朝红. 考虑重构和微电网分区的分布式电源优化配置[J]. 智慧电力, 2020, 48(7):8-15.
	BIAN Yiheng, GUI Hengli, BIE Zhaohong. Optimal DG allocation considering reconfiguration and microgrid zoning[J]. Smart Power, 2020, 48(7):8-15.
[2]	WU Z, ZHAN H Y, GU W, et al. Interval state estimation of distribution network with power flow constraint[J]. IEEE Access, 6: 40826-40835. doi: 10.1109/ACCESS.2018.2856823 URL
[3]	薛艳静, 徐岩, 程姝. 基于电流变化的环状直流配电网故障定位方法[J]. 智慧电力, 2021, 49(2):76-82.
	XUE Yanjing, XU Yan, CHENG Shu. Fault Location Method of Ring DC Distribution Network Based Current Variation[J]. Smart Power, 2021, 49(2):76-82.
[4]	陈鹏浩, 李慧璇, 李锰, 等. 基于改进人工蜂群算法的直流配电网典型应用场景拓扑结构研究[J]. 电力系统保护与控制, 2021, 49(3): 57-65.
	CHEN Penghao, LI Huixuan, LI Meng, et al. Research on the topological structure of typical application scenarios of a DC distribution network based on improved artificial bee colony algorithm[J]. Power System Protection and Control, 2021, 49(3): 57-65.
[5]	王守相, 陈思佳, 谢颂果. 考虑安全约束的交直流配电网储能与换流站协调经济调度[J]. 电力系统自动化, 2017, 41(11): 85-91.
	WANG Shouxiang, CHEN Sijia, XIE Songguo. Security-constrained coordinated economic dispatch of energy storage systems and converter stations for AC/DC distribution networks[J]. Automation of Electric Power Systems, 2017, 41(11): 85-91.
[6]	张志荣, 邱晓燕, 孙旭, 等. 协调柔性负荷与储能的交直流配电网经济优化调度[J]. 电力建设, 2020, 41(5): 116-123. doi: 10.12204/j.issn.1000-7229.2020.05.014
	ZHANG Zhirong, QIU Xiaoyan, SUN Xu, et al. Economic optimal scheduling of AC/DC distribution network coordinating flexible load and energy storage systems[J]. Electric Power Construction, 2020, 41(5): 116-123.
[7]	JU Y T, WU W C, GE F C, et al. Fast decoupled state estimation for distribution networks considering branch ampere measurements[J]. IEEE Transactions on Smart Grid, 2018, 9(6): 6338-6347. doi: 10.1109/TSG.2017.2709463 URL
[8]	孔祥玉, 张烜墉, 王成山, 等. 复杂形态下的配电网自适应自趋优状态估计方法[J]. 中国电机工程学报, 2021, 41(10): 3339-3348.
	KONG Xiangyu, ZHANG Xuanyong, WANG Chengshan, et al. Adaptive self-optimizing state estimation method of distribution network in complex condition[J]. Proceedings of the CSEE, 2021, 41(10): 3339-3348.
[9]	徐俊俊, 戴桂木, 吴在军, 等. 计及电动汽车和光伏不确定性的主动配电网量测优化配置[J]. 电力系统自动化, 2017, 41(1): 57-64.
	XU Junjun, DAI Guimu, WU Zaijun, et al. Optimal meter placement for active distribution network considering uncertainties of plug-in electric vehicles and photovoltaic systems[J]. Automation of Electric Power Systems, 2017, 41(1): 57-64.
[10]	GHASEMI DAMAVANDI M, KRISHNAMURTHY V, MARTÍ J R. Robust meter placement for state estimation in active distribution systems[J]. IEEE Transactions on Smart Grid, 2015, 6(4): 1972-1982. doi: 10.1109/TSG.2015.2394361 URL
[11]	BHELA S, KEKATOS V, VEERAMACHANENI S. Enhancing observability in distribution grids using smart meter data[J]. IEEE Transactions on Smart Grid, 2018, 9(6): 5953-5961. doi: 10.1109/TSG.2017.2699939 URL
[12]	曲正伟, 张嘉曦, 王云静, 等. 考虑分布式电源不确定性的配电网改进仿射状态估计[J]. 电力系统自动化, 2021, 45(23): 104-112.
	QU Zhengwei, ZHANG Jiaxi, WANG Yunjing, et al. Improved affine state estimation for distribution network considering uncertainty of distributed generator[J]. Automation of Electric Power Systems, 2021, 45(23): 104-112.
[13]	SCHLÖSSER T, ANGIONI A, PONCI F, et al. Impact of pseudo-measurements from new load profiles on state estimation in distribution grids[C]// 2014 IEEE International Instrumentation and Measurement Technology Conference (I2MTC) Proceedings. IEEE, : 625-630.
[14]	DEDINEC A, FILIPOSKA S, DEDINEC A,, et al. Deep belief network based electricity load forecasting: An analysis of Macedonian case[J]. Energy, 2016, 115: 1688-1700. doi: 10.1016/j.energy.2016.07.090 URL
[15]	MANITSAS E, SINGH R, PAL B C, et al. Distribution system state estimation using an artificial neural network approach for pseudo measurement modeling[J]. IEEE Transactions on Power Systems, 2012, 27(4): 1888-1896. doi: 10.1109/TPWRS.2012.2187804 URL
[16]	黄蔓云, 孙国强, 卫志农, 等. 基于脉冲神经网络伪量测建模的配电网三相状态估计[J]. 电力系统自动化, 2016, 40(16): 38-43.
	HUANG Manyun, SUN Guoqiang, WEI Zhinong, et al. Three-phase state estimation in distribution systems based on pseudo measurement modeling using spiking neural network[J]. Automation of Electric Power Systems, 2016, 40(16): 38-43.
[17]	雷婧婷, 安婷, 杜正春, 等. 含直流配电网的交直流潮流计算[J]. 中国电机工程学报, 2016, 36(4): 911-918.
	LEI Jingting, AN Ting, DU Zhengchun, et al. A unified AC/DC power flow algorithm with DC distribution[J]. Proceedings of the CSEE, 2016, 36(4): 911-918.
[18]	柴润泽, 窦竟铭, 张保会. 含电压源换流器的交直流混合电网潮流统一表达与可行解求取[J]. 中国电机工程学报, 2016, 36(5): 1260-1268.
	CHAI Runze, DOU Jingming, ZHANG Baohui. Unified power flow expressions and algorithm to obtain feasible solution for hybrid AC/DC grids incorporating VSCs[J]. Proceedings of the CSEE, 2016, 36(5): 1260-1268.
[19]	陈和升, 卫志农, 孙国强, 等. 考虑换流器控制特性的交直流混联微电网状态估计[J]. 电力建设, 2016, 37(5): 91-99.
	CHEN Hesheng, WEI Zhinong, SUN Guoqiang, et al. State estimation of AC-DC hybrid microgrid considering inverter control characteristics[J]. Electric Power Construction, 2016, 37(5): 91-99.
[20]	XIA N, GOOI H B, CHEN S X, et al. Decentralized state estimation for hybrid AC/DC microgrids[J]. IEEE Systems Journal, 2018, 12(1): 434-443. doi: 10.1109/JSYST.2016.2615428 URL
[21]	杨艳红, 裴玮, 邓卫, 等. 计及换流站运行方式的交直流混合配电系统潮流计算方法[J]. 高电压技术, 2016, 42(7): 2149-2157.
	YANG Yanhong, PEI Wei, DENG Wei, et al. Method for calculating power flow of hybrid AC/DC power distribution system with converter station operation mode[J]. High Voltage Engineering, 2016, 42(7): 2149-2157.
[22]	PAU M, SADU A, PILLAI S, et al. A state estimation algorithm for hybrid AC/DC networks with multi-terminal DC grid[C]// 2016 IEEE PES Innovative Smart Grid Technologies Conference Europe. IEEE, 2016: 1-6.
[23]	HUANG M Y, ZHAO J B, WEI Z N, et al. Decentralized robust state estimation for hybrid AC/DC distribution systems with smart meters[J]. International Journal of Electrical Power & Energy Systems, 2022, 136: 107656. doi: 10.1016/j.ijepes.2021.107656 URL
[24]	徐晨博, 周志芳, 高佳宁, 等. DG出力不确定性对交直流混合系统潮流影响的量化分析方法[J]. 电力建设, 2019, 40(3): 102-108. doi: 10.3969/j.issn.1000-7229.2019.03.013
	XU Chenbo, ZHOU Zhifang, GAO Jianing, et al. Quantitative analysis method for the influence of DG’s uncertainty on the power flow of AC/DC hybrid system[J]. Electric Power Construction, 2019, 40(3): 102-108. doi: 10.3969/j.issn.1000-7229.2019.03.013
[25]	鲍威, 凌卫家, 张静, 等. 含VSC-MTDC的交直流混合电网潮流计算模型及稀疏性处理技术[J]. 电力自动化设备, 2016, 36(5): 43-48.
	BAO Wei, LING Weijia, ZHANG Jing, et al. Power flow calculation model and parse matrix disposal techniques for AC/DC hybrid power system with VSC-MTDC[J]. Electric Power Automation Equipment, 2016, 36(5): 43-48.
[26]	SUN F Z, MA J C, YU M, et al. A robust optimal coordinated droop control method for multiple VSCs in AC-DC distribution network[J]. IEEE Transactions on Power Systems, 2019, 34(6): 5002-5011. doi: 10.1109/TPWRS.2019.2919904 URL
[27]	孟雨田, 严正, 徐潇源, 等. 配电网状态估计的全局灵敏度分析及应用[J]. 电力系统自动化, 2020, 44(2): 114-122.
	MENG Yutian, YAN Zheng, XU Xiaoyuan, et al. Global sensitivity analysis on state estimation of distribution network and its application[J]. Automation of Electric Power Systems, 2020, 44(2): 114-122.
[28]	马鑫. 交直流配电网状态估计及日前调度模型研究[D]. 杭州: 浙江大学, 2019.
	MA Xin. State estimation and day-ahead scheduling model for AC/DC distribution network[D]. Hangzhou: Zhejiang University, 2019.
[29]	QI C, WANG K Y, FU Y, et al. A decentralized optimal operation of AC/DC hybrid distribution grids[J]. IEEE Transactions on Smart Grid, 2018, 9(6): 6095-6105. doi: 10.1109/TSG.2017.2703582 URL

基于深度神经网络伪量测建模的交直流混合配电网交替迭代法状态估计

Alternating-Iteration State Estimation of AC/DC Hybrid Distribution System Based on Pseudo-Measurement Modeling Using Deep Neural Network

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

图/表 16

参考文献 29

相关文章 11

编辑推荐

Metrics

本文评价

[1]	宫建锋, 周宗川, 靳盘龙, 张斌, 韩一鸣, 冯雪. 考虑灵活性的交直流混合配电网储能双层规划[J]. 电力建设, 2022, 43(7): 48-56.
[2]	蒙永苹, 张明媚, 向明旭, 杨渝璐, 黄俊凯, 杨知方. 电力系统自然频率特性系数区间预测方法[J]. 电力建设, 2021, 42(9): 105-111.
[3]	庄家懿, 杨国华, 郑豪丰, 王煜东, 胡瑞琨, 丁旭. 并行多模型融合的混合神经网络超短期负荷预测[J]. 电力建设, 2020, 41(10): 1-8.
[4]	黄河，高松，韩俊，孙琦润，吴志，顾伟. 交直流混合配电网分布式电源最大准入容量[J]. 电力建设, 2019, 40(10): 75-83.
[5]	孟明，朱国林，魏怡. 基于最优潮流的交直流配电网分层控制策略[J]. 电力建设, 2018, 39(8): 94-101.
[6]	孙国萌，韩蓓，李国杰. 基于概率方法的全寿命周期交直流混合配电网经济性评估[J]. 电力建设, 2016, 37(5): 21-27.
[7]	尹忠东，王超. 分布式风电接入交直流混合配电网的研究[J]. 电力建设, 2016, 37(5): 63-68.
[8]	陈和升，卫志农，孙国强，陈胜，臧海祥. 考虑换流器控制特性的交直流混联微电网状态估计[J]. 电力建设, 2016, 37(5): 91-99.
[9]	尹忠东，冯寅，闫凤琴，蒋利民. 交直流混合配电网能效综合评价方法[J]. 电力建设, 2016, 37(5): 100-108.
[10]	张伟，韦涛，崔艳妍，刘伟，王宗礼，李芳，黄仁乐. 基于柔性环网控制装置的交直流混合配电网接线模式研究[J]. 电力建设, 2016, 37(12): 32-.
[11]	严逍，焦彦军，杜哲. 基于多端VSC技术的一种交直流混合配电网网络结构[J]. 电力建设, 2016, 37(12): 48-.