基于社区划分的GRU神经网络负荷建模

doi:10.3969/j.issn.2097-0706.2022.02.003

综合智慧能源 ›› 2022, Vol. 44 ›› Issue (2): 15-20.doi: 10.3969/j.issn.2097-0706.2022.02.003

基于社区划分的GRU神经网络负荷建模

赵省军¹(), 张开鹏¹(), 付鑫权²(), 司英莲¹, 刘志栋¹^,^*(), 周登钰¹

1.国网甘肃省电力公司武威供电公司,甘肃武威 733000
2.西华大学电气与电子信息学院,成都 610039

收稿日期:2021-08-03 修回日期:2021-09-18 出版日期:2022-02-25 发布日期:2022-03-07
通讯作者: 刘志栋
作者简介:赵省军（1982）,男,高级工程师,从事新型电力系统构建、电力系统建设工作, zhaoxj@gs.sgcc.com.cn;
张开鹏（1974）,男,高级工程师,从事继电保护、农电管理、变电运行管理、调度管理工作, zhangkpww@gs-sgcc.com.cn;
付鑫权（1997）,男,在读硕士研究生,从事电力系统数据分析及负荷特性分析研究, 745034344@qq.com
基金资助:
国网甘肃省电力公司科技项目(52273018000L)

GRU neural network load modeling based on community division

ZHAO Shengjun¹(), ZHANG Kaipeng¹(), FU Xinquan²(), SI YingLian¹, LIU Zhidong¹^,^*(), ZHOU Dengyu¹

1. State Grid Gansu Electric Power Company Wuwei Power Supply Company,Wuwei 733000,China
2. School of Electrical and Electronic Information,Xihua University,Chengdu 610039,China

Received:2021-08-03 Revised:2021-09-18 Online:2022-02-25 Published:2022-03-07
Contact: LIU Zhidong

摘要/Abstract

摘要：

分布式电源的广泛接入增加了配电网复杂程度,导致负荷模型的描述难度大幅提高。此外,针对网络每个节点分别进行建模以及对整个配电网进行建模的方法难以适用于不断扩大规模的配电网。提出一种基于社区划分的门控循环单元（GRU）神经网络负荷建模方法。通过加文-纽曼（GN）算法对配电网拓扑进行分区处理,基于GRU神经网络分别对各个社区进行负荷建模,并在网络输入特征向量中引入度中心性来衡量节点在网络拓扑中的重要程度。对某地区的10 kV配电网进行建模分析,结果表明所建模型精度及计算效率更高。

关键词: 分布式电源, 负荷模型, 社区划分, 度中心性, GRU神经网络

Abstract:

The extensive access of distributed power supplies increases the complexity of power distribution networks,resulting in the difficulty of the description by load models.In addition,modeling for the whole distribution network and each node in it is inapplicable for the ever-expanding distribution network.Therefore,a Gated Recurrent Unit （GRU） neural network load modeling method based on community division is proposed.Firstly,the GN algorithm is used to partition the topology of the distribution network.Then,load model for each community is constructed based on GRU neural network,in which degree centrality is introduced into the input feature vectors to measure the importance of nodes in the network topology.Finally,modeling analysis is carried out on a 10 kV distribution network.The results show that the proposed modelling mothed is of higher accuracy and computational efficiency.

Key words: distributed generation, load model, community division, degree centrality, GRU neural network

中图分类号:

TK01：TM74

赵省军, 张开鹏, 付鑫权, 司英莲, 刘志栋, 周登钰. 基于社区划分的GRU神经网络负荷建模[J]. 综合智慧能源, 2022, 44(2): 15-20.

ZHAO Shengjun, ZHANG Kaipeng, FU Xinquan, SI YingLian, LIU Zhidong, ZHOU Dengyu. GRU neural network load modeling based on community division[J]. Integrated Intelligent Energy, 2022, 44(2): 15-20.

图/表 7

图1

图2

表1

图3

图4

图5

表2

参考文献 18

[1]	鞠平, 马大强. 电力系统负荷建模 [M]. 2版.北京: 中国电力出版社, 2008.
[2]	李培强, 李欣然, 林舜江. 电力负荷建模研究述评[J]. 电力系统及其自动化学报, 2008,20(5):56-64,123.
	LI Peiqiang, LI Xinran, LIN Shunjiang. Critical review on synjournal load modeling[J]. Proceedings of the CSU-EPSA, 2008,20(5):56-64,123.
[3]	李培强, 曾小军, 李欣然, 等. 基于神经网络的分布式电源统一等效建模及其在PSASP中的应用[J]. 电网技术, 2016,40(4):1224-1229.
	LI Peiqiang, ZENG Xiaojun, LI Xinran, et al. Unified equivalent modeling of distributed generation using artificial neural network and its application in PSASP[J]. Power System Technology, 2016,40(4):1224-1229.
[4]	鞠平, 郭德正, 曹路, 等. 含主动负荷的综合电力负荷建模研究综述与展望[J]. 河海大学学报(自然科学版), 2020,48(4):367-376.
	JU Ping, GUO Dezheng, CAO Lu, et al. Review and prospect of modeling on generalized synjournal electric load containing active loads[J]. Journal of Hohai University(Natural Sciences), 2020,48(4):367-376.
[5]	赵静波, 鞠平, 施佳君, 等. 电力系统负荷建模研究综述与展望[J]. 河海大学学报(自然科学版), 2020,48(1):87-94.
	ZHAO Jingbo, JU Ping, SHI Jiajun, et al. Review and prospects for load modeling of power system[J]. Journal of Hohai University(Natural Sciences), 2020,48(1):87-94.
[6]	黄俊铭, 朱建全, 庄远灿. 基于动态RBF神经网络的广义电力负荷建模[J]. 电网技术, 2018,42(2):591-597.
	HUANG Junming, ZHU Jianquan, ZHUANG Yuancan. Generalized power load modeling based on dynamic RBF neural network[J]. Power System Technology, 2018,42(2):591-597.
[7]	LUO T Y, ZHU J Q, HUANG J M. Generalized power load modeling method with multiple RBF neural network model structures[C]//2018 International Conference on Power System Technology (POWERCON). 2018:417-423.
[8]	LI W B, XING L H, HUANG K Y, et al. Generalized load modeling method based on clustering and neural network[C]//2020 International Conference on Artificial Intelligence in Information and Communication (ICAIIC). 2020:619-622.
[9]	ZENG P, LI H P, HE H B, et al. Dynamic energy management of a microgrid using approximate dynamic programming and deep recurrent neural network learning[J]. IEEE Transactions on Smart Grid, 2019,10(4):4435-4445. doi: 10.1109/TSG.5165411
[10]	CHO K, MERRIENBOER B V, GULCEHRE C, et al. Learning phrase representations using RNN encoder-decoder for statistical machine translation[C]//Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP). 2014:1724-1734.
[11]	LI Y L, YANG J Y, WANG H X, et al. Dynamic equivalent modeling for microgrid based on GRU[C]//Energy Reports, 2020(6):1291-1297.
[12]	魏震波, 关翔友, 刘梁豪. 电网社区结构发现方法及其应用综述[J]. 电网技术, 2020,44(7):2600-2609.
	WEI Zhengbo, GUAN Xiangyou, LIU Lianghao. Overview of power community structure discovery algorithms and thier application in power grid analysis[J]. Power System Technology, 2020,44(7):2600-2609.
[13]	管霖, 吴亮, 卓映君, 等. 面向暂态电压控制的大电网区域划分方法[J]. 电网技术, 2018,42(11):3753-3759.
	GUAN Lin, WU Liang, ZHUO Yingjun, et al. Large power system partitioning method of transient voltage control[J]. Power System Technology, 2018,42(11):3753-3759.
[14]	周炳华, 王洋, 李峰, 等. 城市能源互联网视角下的主动配电网规划设计与策略研究[J]. 华电技术, 2021,43(1):59-65.
	ZHOU Binghua, WANG Yang, LI Feng, et al. Research on active distribution network planning and design strategy from the perspective of urban energy internet[J]. Huadian Technology, 2021,43(1):59-65.
[15]	GIRVAN M, NEWMAN M E J. Community structure in social and biological networks[J]. Proceedings of the National Academy of Sciences of the United States of America, 2002,99(12):7821-7826.
[16]	ZHENG C, WANG S R, LIU Y L, et al. A novel equivalent model of active distribution networks based on LSTM[J]. IEEE transactions on neural networks and learning systems, 2019,30(9):2611-2624. doi: 10.1109/TNNLS.5962385
[17]	姚程文, 杨苹, 刘泽健. 基于CNN-GRU混合神经网络的负荷预测方法[J]. 电网技术, 2020,44(9):3416-3424.
	YAO Chengwen, YANG Ping, LIU Zejian. Load forecasting method based on CNN-GRU hybrid neural network[J]. Power System Technology, 2020,44(9):3416-3424.
[18]	彭维珂, 聂椿明, 陈衡, 等. 基于智能算法的空冷火电机组负荷预测研究[J]. 华电技术, 2021,43(3):57-64.
	PENG Weike, NIE Chunming, CHEN Heng, et al. Study on load forecasting for air cooling thermal power units based on intelligent algorithm[J]. Huadian Technology, 2021,43(3):57-64.

GRU层数	Dense层数	收敛时间/s	均方根误差
2	1	7.71	0.068
2	2	7.62	0.059
3	2	9.20	0.063
3	3	9.13	0.057
4	3	10.82	0.066
4	4	10.91	0.063

负荷模型	训练时间/s	均方根误差
GN-GRU	7.66	0.035
All-GRU	9.13	0.057

基于社区划分的GRU神经网络负荷建模

GRU neural network load modeling based on community division

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

图/表 7

参考文献 18

相关文章 8

编辑推荐

Metrics

本文评价

[1]	郭祚刚, 袁智勇, 徐敏, 雷金勇, 李朋岳, 谈赢杰. 多能互补综合能源系统混合能流计算方法及算例[J]. 综合智慧能源, 2022, 44(7): 58-65.
[2]	王卓容, 石庆鑫. 基于拓扑重构与分布式电源调度的配电网灾后恢复策略[J]. 综合智慧能源, 2022, 44(2): 29-34.
[3]	卞阳, 赵奇剑, 胡水军, 徐华, 曹利, 周念成. 基于云平台的智能配电网电能质量监测预警研究与应用[J]. 华电技术, 2021, 43(1): 31-37.
[4]	周炳华, 王洋, 李峰, 崔金栋, 冉子晗. 城市能源互联网视角下的主动配电网规划设计与策略研究[J]. 华电技术, 2021, 43(1): 59-65.
[5]	刘星，崔双喜. 孤岛与重构相配合的配电网故障恢复策略[J]. 华电技术, 2020, 42(1): 29-34.
[6]	孙洪硕1，胡延林2. 含分布式电源的配网重构改进算法[J]. 华电技术, 2013, 35(12): 4-6.
[7]	钟红梅;张飞飞;叶长青. 含分布式电源配电网潮流问题的解决策略[J]. 华电技术, 2012, 34(5): 33-36.
[8]	黄华;叶萌. 含间歇式分布电源配电网的可靠性评估[J]. 华电技术, 2011, 33(9): 4-6.