基于极限学习机的有源配电网多场景静态电压安全分析

doi:10.12204/j.issn.1000-7229.2021.08.003

电力建设 ›› 2021, Vol. 42 ›› Issue (8): 18-28.doi: 10.12204/j.issn.1000-7229.2021.08.003

• 能源互联网人工智能关键技术及其应用·栏目主持刘友波副教授、胡伟副教授、王迎新主任、顾雨嘉高级工程师· • 上一篇下一篇

基于极限学习机的有源配电网多场景静态电压安全分析

撖晨宇¹, 胥鹏¹, 朱红², 刘少君², 王蓓蓓¹

1.东南大学电气工程学院,南京市 210096
2.国网江苏省电力有限公司南京供电分公司,南京市210000

收稿日期:2020-11-27 出版日期:2021-08-01 发布日期:2021-07-30
作者简介:撖晨宇(1996),男,硕士研究生,主要研究方向为人工智能在电力系统中的应用;
胥鹏 (1994),男,博士研究生,主要从事数据挖掘、人工智能在电力系统中的应用等方面的研究工作;
朱红(1971),硕士,研究员级高级工程师,主要从事电力系统数据挖掘等研究工作;
刘少君(1980),硕士,高级工程师,主要从事电力系统智能化的研究工作;
王蓓蓓(1979),女,博士,副教授,博士生导师,主要研究方向为电力市场、需求侧管理等。
基金资助:
国家电网公司科技项目“电力物联背景下主动配电网电压控制深度强化学习策略研究”

Static Voltage Safety Analysis Based on ELM for Active Distribution Power Grid

HAN Chenyu¹, XU Peng¹, ZHU Hong², LIU Shaojun², WANG Beibei¹

1. Scool of Electrical Engineering,Southeast University, Nanjing 210096, China
2. Nanjing Power Supply Branch of State Grid Jiangsu Electric Power Co., Ltd., Nanjing 210000, China

Received:2020-11-27 Online:2021-08-01 Published:2021-07-30
Supported by:
research program “Research on Deep Reinforcement Learning Strategy of Active Distribution Network Voltage Control under Power Internet of Things”of State Grid Corporation of China

摘要/Abstract

摘要：

随着配电网中分布式可再生能源(distributed renewable generation,DRG)单相接入及其出力波动带来的不确定性增加,DRG接入情景下的配电网过电压、三相不平衡等静态电压安全分析面临新的挑战。为此,提出采用极限学习机模型挖掘配电网的三相潮流计算输入输出之间复杂的映射关系,训练后的网络能够大幅提升不同拓扑结构及不同DRG输出场景下三相潮流的计算效率。基于此提出了一种考虑多场景的有源配电网静态电压安全分析方法,该方法能够快速地对配电网中不同接入节点的安全性做出分析判别。最后采用接入DRG的IEEE 13节点、33节点及118节点系统进行仿真计算。仿真结果表明,所提方法较传统的三相潮流计算方法具有更高的计算速度,且不存在收敛性能上的问题,较BP神经网络方法也具有更高的效率与准确性,验证了所提方法的有效性与实用性。

关键词: 极限学习机, 电压越限分析, 安全分析, 神经网络

Abstract:

With the increase of uncertainty caused by the single phase access of distributed renewable generation (DRG) in the distribution power grid, the static safety analysis for overvoltage and imbalance of the distribution power grid with DRG faces new challenges. This paper proposes to use the extreme learning machine to analyze the complex relationship between the input and output of the three-phase power flow calculations in distribution network. The trained network can greatly improve the efficiency of power flow calculation in different scenarios caused by DRG fluctuations with this topology. On this basis, a voltage safety analysis method considering multiple scenarios of distribution power grid is proposed, which can quickly analyze and judge the safety of grid nodes. Finally, this paper uses IEEE 13-node,IEEE 33-node and IEEE 118-node systems with DRG for simulation calculation. The experimental results show that the method proposed in this paper is more effective than the traditional three-phase power flow calculation method without any convergence problem, and has higher efficiency and accuracy than BP neural network. The effectiveness of the proposed method is verified.

Key words: extreme learning machine, overvoltage analysis, safety analysis, neural network

中图分类号:

TM72

撖晨宇, 胥鹏, 朱红, 刘少君, 王蓓蓓. 基于极限学习机的有源配电网多场景静态电压安全分析[J]. 电力建设, 2021, 42(8): 18-28.

HAN Chenyu, XU Peng, ZHU Hong, LIU Shaojun, WANG Beibei. Static Voltage Safety Analysis Based on ELM for Active Distribution Power Grid[J]. ELECTRIC POWER CONSTRUCTION, 2021, 42(8): 18-28.

图/表 18

参考文献 33

[1]	浙江分布式光伏装机容量居全国第一[EB/OL]. (2018-10-16)[2020-10-08]. https://www.sohu.com/a/259908028_805678.
[2]	裴哲义, 丁杰, 李晨, 等. 分布式光伏并网问题分析与建议[J]. 中国电力, 2018, 51(10): 80-87.
	PEI Zheyi, DING Jie, LI Chen, et al. Analysis and suggestion for distributed photovoltaic generation[J]. Electric Power, 2018, 51(10): 80-87.
[3]	许建峰, 曹庆仁. 中国分布式光伏并网发电现状及应用研究[J]. 能源与节能, 2020(6): 45-48.
	XU Jianfeng, CAO Qingren. Research on the status and application of distributed photovoltaic grid-connected power generation in China[J]. Energy and Energy Conservation, 2020(6): 45-48.
[4]	裴玮, 盛鹍, 孔力, 等. 分布式电源对配网供电电压质量的影响与改善[J]. 中国电机工程学报, 2008, 28(13): 152-157.
	PEI Wei, SHENG Kun, KONG Li, et al. Impact and improvement of distributed generation on distribution network voltage quality[J]. Proceedings of the CSEE, 2008, 28(13): 152-157..
[5]	薛禹胜, 雷兴, 薛峰, 等. 关于风电不确定性对电力系统影响的评述[J]. 中国电机工程学报, 2014, 34(29): 5029-5040.
	XUE Yusheng, LEI Xing, XUE Feng, et al. A review on impacts of wind power uncertainties on power systems[J]. Proceedings of the CSEE, 2014, 34(29): 5029-5040.
[6]	杨茂, 王金鑫. 考虑可再生能源出力不确定的孤岛型微电网优化调度[J]. 中国电机工程学报, 2021, 41(3): 973-984.
	YANG Mao, WANG Jinxin. Optimal scheduling of islanded microgrid considering uncertain output of renewable energy[J]. Proceeding of the CSEE, 2021, 41(3): 973-984.
[7]	丁明, 王伟胜, 王秀丽, 等. 大规模光伏发电对电力系统影响综述[J]. 中国电机工程学报, 2014, 34(1): 1-14.
	DING Ming, WANG Weisheng, WANG Xiuli, et al. A review on the effect of large-scale PV generation on power systems[J]. Proceedings of the CSEE, 2014, 34(1): 1-14.
[8]	唐巍, 蔡永翔, 李天锐, 等. 低压配电网消纳分布式光伏的控制策略及性能分析[J]. 分布式能源, 2018, 3(6): 1-12.
	TANG Wei, CAI Yongxiang, LI Tianrui, et al. Distributed PV consumption control strategy and performance analysis in low voltage distribution network[J]. Distributed Energy, 2018, 3(6): 1-12.
[9]	李清然, 张建成. 含分布式光伏电源的配电网电压越限解决方案[J]. 电力系统自动化, 2015, 39(22): 117-123.
	LI Qingran, ZHANG Jiancheng. Solutions of voltage beyond limits in distribution network with distributed photovoltaic generators[J]. Automation of Electric Power Systems, 2015, 39(22): 117-123..
[10]	叶斌, 李万启, 王绪利, 等. 含分布式新能源的配电网风险规划[J]. 电力建设, 2016, 37(4): 117-123.
	YE Bin, LI Wanqi, WANG Xuli, et al. Risk planning of distribution network with distributed new energy[J]. Electric Power Construction, 2016, 37(4): 117-123.
[11]	郭丽伟, 薛永端, 张林利, 等. 含分布式电源的小电阻接地方式配电网单相接地故障分析[J]. 电力系统自动化, 2015, 39(20): 116-123.
	GUO Liwei, XUE Yongduan, ZHANG Linli, et al. Analysis of single-phase earth fault in low resistance grounded distribution network containing DG[J]. Automation of Electric Power Systems, 2015, 39(20): 116-123.
[12]	GARCIA P A N, PEREIRA J L R, CARNEIRO S, et al. Three-phase power flow calculations using the current injection method[J]. IEEE Transactions on Power Systems, 2000, 15(2): 508-514.. doi: 10.1109/59.867133 URL
[13]	ABDEL-AKHER M, NOR K M, RASHID A H A. Improved three-phase power-flow methods using sequence components[J]. IEEE Transactions on Power Systems, 2005, 20(3): 1389-1397. doi: 10.1109/TPWRS.2005.851933 URL
[14]	任鹏凌. 基于堆栈式降噪自动编码器的概率潮流计算方法[D]. 重庆: 重庆大学, 2018.
	REN Pengling. Probabilistic power flow calculation based on stacked denoising auto-encoders[D]. Chongqing: Chongqing University, 2018.
[15]	王洪涛, 李晓刚, 邹斌. 基于贝叶斯网络刻画风-光-荷相关性的配电网概率潮流计算[J]. 中国电机工程学报, 2019, 39(16): 4753-4763.
	WANG Hongtao, LI Xiaogang, ZOU Bin. Probabilistic load flow calculation of distribution system based on Bayesian network to depict wind-photovoltaic-load correlation[J]. Proceedings of the CSEE, 2019, 39(16): 4753-4763.
[16]	廖剑波. 主动配电网的优化调度与静态安全分析[D]. 上海: 上海电力学院, 2017.
	LIAO Jianbo. Optimal scheduling and static security analysis of active distribution network[D]. Shanghai: Shanghai University of Electric Power, 2017.
[17]	张红, 李生珠, 程跃, 等. 基于时序特性的主动配电网静态安全评价[J]. 科学技术与工程, 2017, 17(24): 233-237.
	ZHANG Hong, LI Shengzhu, CHENG Yue, et al. Safety evaluation of active distribution network based on time sequence characteristics[J]. Science Technology and Engineering, 2017, 17(24): 233-237.
[18]	杨维全, 朱元振, 刘玉田. 基于卷积神经网络的暂态电压稳定快速评估[J]. 电力系统自动化, 2019, 43(22): 46-51.
	YANG Weiquan, ZHU Yuanzhen, LIU Yutian. Fast assessment of transient voltage stability based on convolutional neural network[J]. Automation of Electric Power Systems, 2019, 43(22): 46-51.
[19]	裴宇婷, 秦超, 余贻鑫. 基于LightGBM和DNN的智能配电网在线拓扑辨识[J]. 天津大学学报(自然科学与工程技术版), 2020, 53(9): 939-950.
	PEI Yuting, QIN Chao, YU Yixin. Online topology identification for smart distribution grids based on LightGBM and deep neural networks[J]. Journal of Tianjin University (Science and Technology), 2020, 53(9): 939-950.
[20]	杨燕, 杨知方, 余娟, 等. 基于深度学习的含不确定性N-1安全校核方法[J]. 中国电机工程学报, 2021, 41(8): 2716-2724.
	YANG Yan, YANG Zhifang, YU Juan, et al. Fast analysis of N-1 contingency screening with uncertainty scenarios based on deep learning[J]. Proceeding of the CSEE, 2021, 41(8): 2716-2724.
[21]	范晓龙, 何健, 刘汇川, 等. 含多类型分布式电源的主动配电网三相潮流计算[J]. 陕西电力, 2016, 44(12): 11-17.
	FAN Xiaolong, HE Jian, LIU Huichuan, et al. Three-phase power flow computation for active distribution networks with different types of distribution generations[J]. Shaanxi Electric Power, 2016, 44(12): 11-17.
[22]	周步祥, 邓苏娟, 张百甫. 基于RBF神经网络和无迹变换法的三相概率潮流计算[J]. 电测与仪表, 2018, 55(11): 7-11.
	ZHOU Buxiang, DENG Sujuan, ZHANG Baifu. Three-phase probabilistic power flow calculation based on RBF neural network and unscented transformation algorithm[J]. Electrical Measurement & Instrumentation, 2018, 55(11): 7-11.
[23]	AIEN M, FOTUHI-FIRUZABAD M, RASHIDINEJAD M. Probabilistic optimal power flow in correlated hybrid wind-photovoltaic power systems[J]. IEEE Transactions on Smart Grid, 2014, 5(1): 130-138. doi: 10.1109/TSG.2013.2293352 URL
[24]	董树锋, 章杜锡, 周飞, 等. 一种基于回路电流法的有源配电网潮流算法[J]. 电力自动化设备, 2018, 38(2): 9-17.
	DONG Shufeng, ZHANG Duxi, ZHOU Fei, et al. Loop-current method based power flow algorithm for active distribution network[J]. Electric Power Automation Equipment, 2018, 38(2): 9-17.
[25]	朱城香, 杨俊华, 陈思哲, 等. GridLAB-D智能仿真软件及其应用[J]. 水力发电, 2015, 41(4): 74-78.
	ZHU Chengxiang, YANG Junhua, CHEN Sizhe, et al. GridLAB-D agent simulation software and its application[J]. Water Power, 2015, 41(4): 74-78.
[26]	HUANG G B. Learning capability and storage capacity of two-hidden-layer feedforward networks[J]. IEEE Transactions on Neural Networks, 2003, 14(2): 274-281. doi: 10.1109/TNN.2003.809401 URL
[27]	HUANG G B, CHEN L, SIEW C K. Universal approximation using incremental constructive feedforward networks with random hidden nodes[J]. IEEE Transactions on Neural Networks, 2006, 17(4): 879-892. doi: 10.1109/TNN.2006.875977 URL
[28]	牛铭, 黄伟, 郭佳欢, 等. 微网并网时的经济运行研究[J]. 电网技术, 2010, 34(11): 38-42.
	NIU Ming, HUANG Wei, GUO Jiahuan, et al. Research on economic operation of grid-connected microgrid[J]. Power System Technology, 2010, 34(11): 38-42.
[29]	李海南, 张建华, 朱星阳, 等. 计及天气影响的含风电场电力系统风险评估[J]. 华东电力, 2014, 42(6): 1084-1091.
	LI Hainan, ZHANG Jianhua, ZHU Xingyang, et al. Risk assessment of power system with wind farm considering weather impacts[J]. East China Electric Power, 2014, 42(6): 1084-1091.
[30]	周林, 张有玉, 刘强, 等. 三相不平衡度算法的比较研究[J]. 华东电力, 2010, 38(2): 210-215.
	ZHOU Lin, ZHANG Youyu, LIU Qiang, et al. Comparative study of three-phase unbalance algorithm[J]. East China Electric Power, 2010, 38(2): 210-215.
[31]	ISLAM S A U, RATNAM E L, GOEL A, et al. Phasor-based adaptive control of a test-feeder distribution network: Application of retrospective cost adaptive control to the IEEE 13-node test feeder[J]. IEEE Control Systems Magazine, 2019, 39(4): 56-74. doi: 10.1109/MCS.2019.2913611 URL
[32]	叶倩莹. 基于深度神经网络的可变拓扑电网潮流计算方法研究[D]. 杭州: 浙江大学, 2019.
	YE Qianying. Power flow for grids with unfixed topologies by using deep neural network[D]. Hangzhou: Zhejiang University, 2019.
[33]	张可华. 配电网调度自动化馈线终端单元的研究与设计[D]. 锦州: 辽宁工业大学, 2016.
	ZHANG Kehua. Research and design of feeder terminal unit of distribution network dispatching automation[D]. Jinzhou, China: Liaoning University of Technology, 2016.

节点编号	V_max /pu	V_min/pu	P/MW	Q/ (MV·A)	节点编号	V_max /pu	V_min/pu	P/MW	Q/ (MV·A)	节点编号	V_max /pu	V_min/pu	P/MW	Q/ (MV·A)
1	1.06	0.94	51	27	41	1.06	0.94	34	0	81	1.06	0.94	11	7
2	1.06	0.94	20	9	42	1.06	0.94	20	11	82	1.06	0.94	24	15
3	1.06	0.94	14	1	43	1.06	0.94	52	22	83	1.06	0.94	21	10
4	1.06	0.94	90	30	44	1.06	0.94	87	30	84	1.06	0.94	70	23
5	1.06	0.94	25	10	45	1.06	0.94	17	4	85	1.06	0.94	48	10
6	1.06	0.94	25	10	46	1.06	0.94	17	8	86	1.06	0.94	163	42
7	1.06	0.94	11	3	47	1.06	0.94	18	5	87	1.06	0.94	10	0
8	1.06	0.94	60	34	48	1.06	0.94	23	11	88	1.06	0.94	10	0
9	1.06	0.94	45	25	49	1.06	0.94	113	32	89	1.06	0.94	38	15
10	1.06	0.94	18	3	50	1.06	0.94	63	22	90	1.06	0.94	65	10
11	1.06	0.94	45	25	51	1.06	0.94	84	18	91	1.06	0.94	12	7
12	1.06	0.94	18	3	52	1.06	0.94	12	3	92	1.06	0.94	30	16
13	1.06	0.94	14	8	53	1.06	0.94	12	3	93	1.06	0.94	42	31
14	1.06	0.94	10	5	54	1.06	0.94	19	2	94	1.06	0.94	38	15
15	1.06	0.94	7	3	55	1.06	0.94	277	113	95	1.06	0.94	15	9
16	1.06	0.94	39	10	56	1.06	0.94	78	3	96	1.06	0.94	34	8
17	1.06	0.94	13	0	57	1.06	0.94	77	14	97	1.06	0.94	47	10
18	1.06	0.94	71	13	58	1.06	0.94	39	18	98	1.06	0.94	42	0
19	1.06	0.94	17	7	59	1.06	0.94	28	7	99	1.06	0.94	37	18
20	1.06	0.94	24	4	60	1.06	0.94	66	20	100	1.06	0.94	22	15
21	1.06	0.94	43	27	61	1.06	0.94	66	20	101	1.06	0.94	5	3
22	1.06	0.94	59	23	62	1.06	0.94	12	0	102	1.06	0.94	23	16
23	1.06	0.94	23	9	63	1.06	0.94	78	3	103	1.06	0.94	38	25
24	1.06	0.94	59	26	64	1.06	0.94	77	14	104	1.06	0.94	31	26
25	1.06	0.94	23	9	65	1.06	0.94	39	18	105	1.06	0.94	43	16
26	1.06	0.94	59	26	66	1.06	0.94	6	0	106	1.06	0.94	50	12
27	1.06	0.94	33	9	67	1.06	0.94	68	27	107	1.06	0.94	2	1
28	1.06	0.94	31	17	68	1.06	0.94	6	0	108	1.06	0.94	34	16
29	1.06	0.94	39	12	69	1.06	0.94	68	27	109	1.06	0.94	8	3
30	1.06	0.94	27	11	70	1.06	0.94	47	11	110	1.06	0.94	39	30
31	1.06	0.94	27	11	71	1.06	0.94	68	36	111	1.06	0.94	22	7
32	1.06	0.94	66	23	72	1.06	0.94	28	0	112	1.06	0.94	68	13
33	1.06	0.94	37	10	73	1.06	0.94	68	36	113	1.06	0.94	6	0
34	1.06	0.94	96	23	74	1.06	0.94	61	28	114	1.06	0.94	8	3
35	1.06	0.94	18	7	75	1.06	0.94	71	26	115	1.06	0.94	22	7
36	1.06	0.94	16	8	76	1.06	0.94	39	32	116	1.06	0.94	184	0
37	1.06	0.94	18	7	77	1.06	0.94	130	26	117	1.06	0.94	20	8
38	1.06	0.94	16	8	78	1.06	0.94	54	27	118	1.06	0.94	33	15
39	1.06	0.94	53	22	79	1.06	0.94	20	10
40	1.06	0.94	28	10	80	1.06	0.94	11	7

节点编号	V_max /pu	V_min/pu	P/MW	Q/ (MV·A)	节点编号	V_max /pu	V_min/pu	P/MW	Q/ (MV·A)	节点编号	V_max /pu	V_min/pu	P/MW	Q/ (MV·A)
1	1.06	0.94	51	27	41	1.06	0.94	34	0	81	1.06	0.94	11	7
2	1.06	0.94	20	9	42	1.06	0.94	20	11	82	1.06	0.94	24	15
3	1.06	0.94	14	1	43	1.06	0.94	52	22	83	1.06	0.94	21	10
4	1.06	0.94	90	30	44	1.06	0.94	87	30	84	1.06	0.94	70	23
5	1.06	0.94	25	10	45	1.06	0.94	17	4	85	1.06	0.94	48	10
6	1.06	0.94	25	10	46	1.06	0.94	17	8	86	1.06	0.94	163	42
7	1.06	0.94	11	3	47	1.06	0.94	18	5	87	1.06	0.94	10	0
8	1.06	0.94	60	34	48	1.06	0.94	23	11	88	1.06	0.94	10	0
9	1.06	0.94	45	25	49	1.06	0.94	113	32	89	1.06	0.94	38	15
10	1.06	0.94	18	3	50	1.06	0.94	63	22	90	1.06	0.94	65	10
11	1.06	0.94	45	25	51	1.06	0.94	84	18	91	1.06	0.94	12	7
12	1.06	0.94	18	3	52	1.06	0.94	12	3	92	1.06	0.94	30	16
13	1.06	0.94	14	8	53	1.06	0.94	12	3	93	1.06	0.94	42	31
14	1.06	0.94	10	5	54	1.06	0.94	19	2	94	1.06	0.94	38	15
15	1.06	0.94	7	3	55	1.06	0.94	277	113	95	1.06	0.94	15	9
16	1.06	0.94	39	10	56	1.06	0.94	78	3	96	1.06	0.94	34	8
17	1.06	0.94	13	0	57	1.06	0.94	77	14	97	1.06	0.94	47	10
18	1.06	0.94	71	13	58	1.06	0.94	39	18	98	1.06	0.94	42	0
19	1.06	0.94	17	7	59	1.06	0.94	28	7	99	1.06	0.94	37	18
20	1.06	0.94	24	4	60	1.06	0.94	66	20	100	1.06	0.94	22	15
21	1.06	0.94	43	27	61	1.06	0.94	66	20	101	1.06	0.94	5	3
22	1.06	0.94	59	23	62	1.06	0.94	12	0	102	1.06	0.94	23	16
23	1.06	0.94	23	9	63	1.06	0.94	78	3	103	1.06	0.94	38	25
24	1.06	0.94	59	26	64	1.06	0.94	77	14	104	1.06	0.94	31	26
25	1.06	0.94	23	9	65	1.06	0.94	39	18	105	1.06	0.94	43	16
26	1.06	0.94	59	26	66	1.06	0.94	6	0	106	1.06	0.94	50	12
27	1.06	0.94	33	9	67	1.06	0.94	68	27	107	1.06	0.94	2	1
28	1.06	0.94	31	17	68	1.06	0.94	6	0	108	1.06	0.94	34	16
29	1.06	0.94	39	12	69	1.06	0.94	68	27	109	1.06	0.94	8	3
30	1.06	0.94	27	11	70	1.06	0.94	47	11	110	1.06	0.94	39	30
31	1.06	0.94	27	11	71	1.06	0.94	68	36	111	1.06	0.94	22	7
32	1.06	0.94	66	23	72	1.06	0.94	28	0	112	1.06	0.94	68	13
33	1.06	0.94	37	10	73	1.06	0.94	68	36	113	1.06	0.94	6	0
34	1.06	0.94	96	23	74	1.06	0.94	61	28	114	1.06	0.94	8	3
35	1.06	0.94	18	7	75	1.06	0.94	71	26	115	1.06	0.94	22	7
36	1.06	0.94	16	8	76	1.06	0.94	39	32	116	1.06	0.94	184	0
37	1.06	0.94	18	7	77	1.06	0.94	130	26	117	1.06	0.94	20	8
38	1.06	0.94	16	8	78	1.06	0.94	54	27	118	1.06	0.94	33	15
39	1.06	0.94	53	22	79	1.06	0.94	20	10
40	1.06	0.94	28	10	80	1.06	0.94	11	7

出发节点	到达节点	电容/ (nF·km^-1)	电阻/ (Ω·km^-1)	电抗/ (Ω·km^-1)	出发节点	到达节点	电容/ (nF·km^-1)	电阻/ (Ω·km^-1)	电抗/ (Ω·km^-1)	出发节点	到达节点	电容/ (nF·km^-1)	电阻/ (Ω·km^-1)	电抗/ (Ω·km^-1)
0	1	353.79	5.77	19.02	36	38	376.08	6.11	20.18	75	76	512.58	8.46	28.18
0	2	150.71	2.46	8.07	36	39	585.01	11.29	31.99	75	117	188.87	3.12	10.35
1	11	218.96	3.56	11.73	37	64	2 331.10	10.72	117.30	76	77	176.06	0.72	2.36
2	4	395.58	4.59	20.56	38	39	216.17	3.50	11.52	76	79	657.43	3.24	9.24
2	11	565.51	9.22	30.47	39	40	170.21	2.76	9.27	76	81	1 138.53	5.68	16.24
3	4	29.25	0.34	1.52	39	41	649.08	10.56	34.85	77	78	90.26	1.04	4.65
3	10	243.47	3.98	13.10	40	41	479.15	7.81	25.70	78	79	260.47	2.97	13.40
4	5	198.62	2.27	10.28	41	48	1 197.86	13.61	61.51	79	95	688.08	6.78	34.66
4	10	242.08	3.87	12.98	42	43	845.19	11.57	46.73	79	96	353.79	3.49	17.78
5	6	76.61	0.87	3.96	43	44	312.00	4.27	17.15	79	97	398.36	4.53	20.56
6	11	121.74	1.64	6.47	44	45	462.43	7.62	25.82	79	98	760.51	8.65	39.23
7	8	2 589.62	2.90	36.30	44	48	618.43	13.02	35.42	81	82	528.73	2.13	6.98
7	29	1 145.49	5.13	59.98	45	46	440.15	7.24	24.18	81	95	757.72	3.09	10.09
8	9	2 741.16	3.07	38.32	45	47	657.43	11.44	35.99	82	83	359.36	11.90	25.13
10	11	69.92	1.13	3.73	46	48	223.42	3.64	11.90	82	84	484.72	8.19	28.18
10	12	261.30	4.24	13.92	46	68	987.82	16.07	52.90	83	84	171.88	5.75	12.20
11	13	252.95	4.09	13.46	47	48	175.22	3.41	9.62	84	85	384.43	6.67	23.42
11	15	298.07	4.04	15.88	48	49	261.02	5.08	14.32	84	87	384.43	3.81	19.42
11	116	498.65	6.27	26.66	48	50	476.36	9.26	26.09	84	88	654.65	4.55	32.94
12	14	873.05	14.16	46.54	48	53	1 027.93	13.90	55.03	87	88	269.38	2.65	13.55
13	14	699.22	11.33	37.13	48	65	345.43	3.43	17.50	88	89	735.44	9.86	35.80
14	16	618.43	2.51	8.32	48	68	1 153.29	18.75	61.70	88	91	763.29	1.89	9.62
14	18	140.68	2.29	7.50	49	56	462.43	9.03	25.51	89	90	298.07	4.84	15.92
14	32	444.88	7.24	23.69	50	51	194.44	3.87	11.19	90	91	455.19	7.37	24.22
15	16	649.08	8.65	34.29	50	57	249.05	4.86	13.69	91	92	303.65	4.91	16.14
16	17	180.79	2.34	9.62	51	52	565.23	7.71	31.13	91	93	565.51	9.16	30.08
16	30	555.76	9.03	29.76	52	53	431.79	5.01	23.23	91	99	657.43	12.34	56.17
16	112	106.97	1.74	5.73	53	54	281.36	3.22	13.46	91	101	203.92	2.34	10.64
17	18	159.07	2.13	9.39	53	55	101.96	0.52	1.82	92	93	261.3	4.25	13.94
18	19	415.08	4.80	22.28	53	58	832.94	9.58	43.66	93	94	154.61	2.51	8.27
18	33	880.29	14.32	47.03	54	55	52.09	0.93	2.88	93	95	320.36	5.12	16.54
19	20	300.86	3.49	16.16	54	58	786.41	9.02	41.09	93	99	841.29	3.39	11.04
20	21	342.65	3.98	18.47	55	56	337.07	6.53	18.39	94	95	205.31	3.26	10.41
21	22	562.72	6.51	30.27	55	57	337.07	6.53	18.39	95	96	334.29	3.29	16.85
22	23	693.65	2.57	9.37	55	58	792.54	15.71	47.80	97	99	663.01	7.56	34.08
22	24	1 203.44	2.97	15.23	58	59	523.72	6.04	27.61	98	99	300.86	3.43	15.48
22	31	1 633.83	6.04	21.95	58	60	540.43	6.25	28.56	99	100	456.86	5.28	24.03
23	69	1 420.44	0.42	78.36	59	60	202.80	0.50	2.57	99	102	746.58	3.05	10.00
23	71	679.72	9.29	37.32	59	61	204.47	2.34	10.68	99	103	753.54	8.59	38.84
24	26	2 457.02	6.06	31.04	60	61	136.50	1.57	7.16	99	105	863.58	11.52	43.61
25	29	2 023.56	9.51	102.30	61	65	805.08	9.18	41.51	100	101	409.50	4.68	21.32
26	27	300.86	3.64	16.28	61	66	431.79	4.91	22.28	102	103	566.90	8.87	30.16
26	31	268.27	4.36	14.37	62	63	481.38	2.05	23.80	102	104	568.29	10.18	30.94
26	114	274.67	3.12	14.11	63	64	846.87	3.20	35.94	102	109	642.11	7.44	34.52
27	28	331.50	4.51	17.95	65	66	373.57	4.27	19.32	103	104	137.34	1.89	7.20
28	30	115.61	2.06	6.30	68	69	1 699.30	5.71	24.18	104	105	199.74	2.67	10.41
29	37	940.47	5.52	64.27	68	74	1 727.15	7.71	23.23	104	106	657.43	10.09	34.85
30	31	349.61	5.68	18.75	68	76	1 445.79	5.88	19.23	104	107	256.85	4.97	13.38
31	112	721.51	11.71	38.65	69	70	122.29	1.68	6.76	105	106	657.43	10.09	34.85
31	113	226.76	2.57	11.65	69	73	469.12	7.64	25.19	107	108	105.86	2.00	5.48
32	36	509.79	7.90	27.04	69	74	501.43	8.15	26.85	108	109	281.36	5.29	14.51
33	35	79.12	1.66	5.10	70	71	618.99	8.49	34.27	109	110	278.57	4.19	14.37
33	36	137.06	0.49	1.79	70	72	164.08	1.65	8.65	109	111	863.58	4.70	12.18
33	42	588.63	7.87	32.01	73	74	144.02	2.34	7.73	113	114	38.44	0.44	1.98
34	35	37.33	0.43	1.94	74	76	693.37	11.44	38.06
34	36	183.58	2.09	9.46	74	117	166.87	2.76	9.16

出发节点	到达节点	电容/ (nF·km^-1)	电阻/ (Ω·km^-1)	电抗/ (Ω·km^-1)	出发节点	到达节点	电容/ (nF·km^-1)	电阻/ (Ω·km^-1)	电抗/ (Ω·km^-1)	出发节点	到达节点	电容/ (nF·km^-1)	电阻/ (Ω·km^-1)	电抗/ (Ω·km^-1)
0	1	353.79	5.77	19.02	36	38	376.08	6.11	20.18	75	76	512.58	8.46	28.18
0	2	150.71	2.46	8.07	36	39	585.01	11.29	31.99	75	117	188.87	3.12	10.35
1	11	218.96	3.56	11.73	37	64	2 331.10	10.72	117.30	76	77	176.06	0.72	2.36
2	4	395.58	4.59	20.56	38	39	216.17	3.50	11.52	76	79	657.43	3.24	9.24
2	11	565.51	9.22	30.47	39	40	170.21	2.76	9.27	76	81	1 138.53	5.68	16.24
3	4	29.25	0.34	1.52	39	41	649.08	10.56	34.85	77	78	90.26	1.04	4.65
3	10	243.47	3.98	13.10	40	41	479.15	7.81	25.70	78	79	260.47	2.97	13.40
4	5	198.62	2.27	10.28	41	48	1 197.86	13.61	61.51	79	95	688.08	6.78	34.66
4	10	242.08	3.87	12.98	42	43	845.19	11.57	46.73	79	96	353.79	3.49	17.78
5	6	76.61	0.87	3.96	43	44	312.00	4.27	17.15	79	97	398.36	4.53	20.56
6	11	121.74	1.64	6.47	44	45	462.43	7.62	25.82	79	98	760.51	8.65	39.23
7	8	2 589.62	2.90	36.30	44	48	618.43	13.02	35.42	81	82	528.73	2.13	6.98
7	29	1 145.49	5.13	59.98	45	46	440.15	7.24	24.18	81	95	757.72	3.09	10.09
8	9	2 741.16	3.07	38.32	45	47	657.43	11.44	35.99	82	83	359.36	11.90	25.13
10	11	69.92	1.13	3.73	46	48	223.42	3.64	11.90	82	84	484.72	8.19	28.18
10	12	261.30	4.24	13.92	46	68	987.82	16.07	52.90	83	84	171.88	5.75	12.20
11	13	252.95	4.09	13.46	47	48	175.22	3.41	9.62	84	85	384.43	6.67	23.42
11	15	298.07	4.04	15.88	48	49	261.02	5.08	14.32	84	87	384.43	3.81	19.42
11	116	498.65	6.27	26.66	48	50	476.36	9.26	26.09	84	88	654.65	4.55	32.94
12	14	873.05	14.16	46.54	48	53	1 027.93	13.90	55.03	87	88	269.38	2.65	13.55
13	14	699.22	11.33	37.13	48	65	345.43	3.43	17.50	88	89	735.44	9.86	35.80
14	16	618.43	2.51	8.32	48	68	1 153.29	18.75	61.70	88	91	763.29	1.89	9.62
14	18	140.68	2.29	7.50	49	56	462.43	9.03	25.51	89	90	298.07	4.84	15.92
14	32	444.88	7.24	23.69	50	51	194.44	3.87	11.19	90	91	455.19	7.37	24.22
15	16	649.08	8.65	34.29	50	57	249.05	4.86	13.69	91	92	303.65	4.91	16.14
16	17	180.79	2.34	9.62	51	52	565.23	7.71	31.13	91	93	565.51	9.16	30.08
16	30	555.76	9.03	29.76	52	53	431.79	5.01	23.23	91	99	657.43	12.34	56.17
16	112	106.97	1.74	5.73	53	54	281.36	3.22	13.46	91	101	203.92	2.34	10.64
17	18	159.07	2.13	9.39	53	55	101.96	0.52	1.82	92	93	261.3	4.25	13.94
18	19	415.08	4.80	22.28	53	58	832.94	9.58	43.66	93	94	154.61	2.51	8.27
18	33	880.29	14.32	47.03	54	55	52.09	0.93	2.88	93	95	320.36	5.12	16.54
19	20	300.86	3.49	16.16	54	58	786.41	9.02	41.09	93	99	841.29	3.39	11.04
20	21	342.65	3.98	18.47	55	56	337.07	6.53	18.39	94	95	205.31	3.26	10.41
21	22	562.72	6.51	30.27	55	57	337.07	6.53	18.39	95	96	334.29	3.29	16.85
22	23	693.65	2.57	9.37	55	58	792.54	15.71	47.80	97	99	663.01	7.56	34.08
22	24	1 203.44	2.97	15.23	58	59	523.72	6.04	27.61	98	99	300.86	3.43	15.48
22	31	1 633.83	6.04	21.95	58	60	540.43	6.25	28.56	99	100	456.86	5.28	24.03
23	69	1 420.44	0.42	78.36	59	60	202.80	0.50	2.57	99	102	746.58	3.05	10.00
23	71	679.72	9.29	37.32	59	61	204.47	2.34	10.68	99	103	753.54	8.59	38.84
24	26	2 457.02	6.06	31.04	60	61	136.50	1.57	7.16	99	105	863.58	11.52	43.61
25	29	2 023.56	9.51	102.30	61	65	805.08	9.18	41.51	100	101	409.50	4.68	21.32
26	27	300.86	3.64	16.28	61	66	431.79	4.91	22.28	102	103	566.90	8.87	30.16
26	31	268.27	4.36	14.37	62	63	481.38	2.05	23.80	102	104	568.29	10.18	30.94
26	114	274.67	3.12	14.11	63	64	846.87	3.20	35.94	102	109	642.11	7.44	34.52
27	28	331.50	4.51	17.95	65	66	373.57	4.27	19.32	103	104	137.34	1.89	7.20
28	30	115.61	2.06	6.30	68	69	1 699.30	5.71	24.18	104	105	199.74	2.67	10.41
29	37	940.47	5.52	64.27	68	74	1 727.15	7.71	23.23	104	106	657.43	10.09	34.85
30	31	349.61	5.68	18.75	68	76	1 445.79	5.88	19.23	104	107	256.85	4.97	13.38
31	112	721.51	11.71	38.65	69	70	122.29	1.68	6.76	105	106	657.43	10.09	34.85
31	113	226.76	2.57	11.65	69	73	469.12	7.64	25.19	107	108	105.86	2.00	5.48
32	36	509.79	7.90	27.04	69	74	501.43	8.15	26.85	108	109	281.36	5.29	14.51
33	35	79.12	1.66	5.10	70	71	618.99	8.49	34.27	109	110	278.57	4.19	14.37
33	36	137.06	0.49	1.79	70	72	164.08	1.65	8.65	109	111	863.58	4.70	12.18
33	42	588.63	7.87	32.01	73	74	144.02	2.34	7.73	113	114	38.44	0.44	1.98
34	35	37.33	0.43	1.94	74	76	693.37	11.44	38.06
34	36	183.58	2.09	9.46	74	117	166.87	2.76	9.16

基于极限学习机的有源配电网多场景静态电压安全分析

Static Voltage Safety Analysis Based on ELM for Active Distribution Power Grid

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

图/表 18

参考文献 33

相关文章 15

编辑推荐

Metrics

本文评价

[1]	高子轩, 赵晋斌, 杨旭红, 姚凤军, 方剑峰. 基于RBF的VSG转动惯量和阻尼系数自适应控制策略[J]. 电力建设, 2022, 43(9): 132-139.
[2]	张金良, 贾凡. 中国火电行业多模型碳达峰情景预测[J]. 电力建设, 2022, 43(5): 18-28.
[3]	杨月, 孙博, 马晓忱, 罗雅迪, 孙英云. 融合注意力机制的输电线路故障概率预测模型[J]. 电力建设, 2022, 43(3): 42-49.
[4]	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.
[5]	李贤初, 张翕, 刘杰, 胡建林. 输电线路导线覆冰AMPSO-BP神经网络预测模型[J]. 电力建设, 2021, 42(9): 140-146.
[6]	彭雨筝, 李晓露, 李聪利, 丁一. 基于残差卷积自编码的风光荷场景生成方法[J]. 电力建设, 2021, 42(8): 10-17.
[7]	黄冬梅, 庄兴科, 胡安铎, 孙锦中, 时帅, 孙园, 唐振. 基于灰色关联分析和K均值聚类的短期负荷预测[J]. 电力建设, 2021, 42(7): 110-117.
[8]	薛溟枫, 毛晓波, 潘湧涛, 杨艳红, 赵振兴, 李彦君. 基于LSTM神经网络的电动汽车充电站需求响应特性封装及配电网优化运行[J]. 电力建设, 2021, 42(6): 76-85.
[9]	王远东, 史文江, 韩兴波, 蒋兴良, 张超, 张志劲. 基于声发射特性的玻璃绝缘子污闪预测模型[J]. 电力建设, 2021, 42(5): 138-144.
[10]	刘仲民, 侯坤福, 高敬更, 王治国. 基于时间卷积神经网络的非侵入式居民用电负荷分解方法[J]. 电力建设, 2021, 42(3): 97-106.
[11]	王珺, 田恩东, 马建, 窦晓波, 刘之涵. 基于数据驱动的非全实时观测配电网无功优化方法[J]. 电力建设, 2021, 42(2): 68-76.
[12]	仝瑞宁, 李鹏, 郎恂, 沈鑫, 曹敏. 基于Fisher主元分析和核极限学习机的非侵入式电力负荷辨识模型[J]. 电力建设, 2021, 42(2): 85-92.
[13]	徐会芳, 张中浩, 谈元鹏, 韩富佳. 面向电网调度领域的实体识别技术[J]. 电力建设, 2021, 42(10): 71-77.
[14]	张凌浩, 张明, 嵇文路, 方磊, 秦羽飞, 葛磊蛟. 基于灰色关联理论和BP神经网络的分布式光伏电站运维数据虚拟采集方法[J]. 电力建设, 2021, 42(1): 125-131.
[15]	唐子卓, 刘洋, 许立雄, 郭久亿. 基于负荷数据频域特征和LSTM网络的类别不平衡负荷典型用电模式提取方法[J]. 电力建设, 2020, 41(8): 17-24.