Leakage Fault Identification of PV-Integrated Distribution Networks Based on CEEMDAN and NRBO-XGBoost

doi:10.11930/j.issn.1004-9649.202501003

Abstract

Abstract:

To address the problem that existing residual current protection devices are difficult to accurately identify leakage faults in the PV-integrated distribution networks, a leakage fault identification model for photovoltaic-integrated distribution networks based on complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) and Newton-Raphson-based optimizer-eXtreme Gradient Boosting (NRBO-XGBoost) is presented. Firstly, the CEEMDAN is used to decompose different leakage signals of the PV-integrated distribution networks. Then, the energy entropy of each decomposed modal component is extracted to construct the leakage fault feature set. Finally, the energy entropy features are input into the NRBO-XGBoost model to achieve the recognition of different leakage states of PV-integrated distribution networks. The effectiveness of the proposed method is verified by the simulation data. The results show that compared with other models, the proposed method has the highest recognition accuracy.

Key words: photovoltaic power supply, distribution network, Newton-Raphson-based optimizer, extreme gradient boosting, leakage fault identification

LIU Han, LIU Jindong, LI He, LI Yanli, YU Qiyuan, ZHAO Yuan, GENG Yanan. Leakage Fault Identification of PV-Integrated Distribution Networks Based on CEEMDAN and NRBO-XGBoost[J]. Electric Power, 2025, 58(9): 23-32.

Add to citation manager EndNote|Ris|BibTeX

URL: https://www.electricpower.com.cn/EN/10.11930/j.issn.1004-9649.202501003

https://www.electricpower.com.cn/EN/Y2025/V58/I9/23

Figures/Tables 13

References 25

1	杜松怀. 电力系统接地技术[M]. 北京: 中国电力出版社, 2011: 25–55.
2	MITOLO M. Shock hazard in the presence of protective residual-current devices[J]. IEEE Transactions on Industry Applications, 2010, 46 (4): 1552- 1557.
3	PARISE G. A new summary on the IEC protection against electric shock[J]. IEEE Transactions on Industry Applications, 2013, 49 (2): 1004- 1011. DOI
4	翟苏巍, 李银银, 杜凡, 等. 考虑海量分布式能源接入的配电网分布式无功控制策略[J]. 中国电力, 2024, 57 (8): 138- 144. DOI
	ZHAI Suwei, LI Yinyin, DU Fan, et al. Distributed reactive power control strategy of distribution network considering massive distributed energy access[J]. Electric Power, 2024, 57 (8): 138- 144. DOI
5	周洋, 黄德志, 李培栋, 等. 考虑平衡端点相位不对称及光伏接入的低压配电网三相潮流模型[J]. 中国电力, 2024, 57 (10): 190- 198.
	ZHOU Yang, HUANG Dezhi, LI Peidong, et al. A three-phase power flow model for low-voltage distribution networks considering balanced bus phase asymmetry and photovoltaic access[J]. Electric Power, 2024, 57 (10): 190- 198.
6	胡满琳, 李楠, 李一鸣, 等. 基于负序分量的含光伏电源配电网故障区段定位方法[J]. 中国电力, 2024, 57 (5): 188- 199. DOI
	HU Manlin, LI Nan, LI Yiming, et al. Fault location method for distribution network with photovoltaic power based on negative sequence component[J]. Electric Power, 2024, 57 (5): 188- 199. DOI
7	王伟, 朱江, 魏兴慎, 等. 面向新型配电系统的网络安全脆弱性评估[J]. 电力信息与通信技术, 2024, 22 (8): 37- 44.
	WANG Wei, ZHU Jiang, WEI Xingshen. Network security vulnerability assessment for new distribution systems[J]. Electric Power Information and Communication Technology, 2024, 22 (8): 37- 44.
8	慕静茹, 喻锟, 曾祥君, 等. 考虑多扰动因子的含光伏电源低压台区漏电故障检测[J]. 南方电网技术, 2024, 18 (10): 130- 141.
	MU Jingru, YU Kun, ZENG Xiangjun, et al. Leakage fault detection in low-voltage station area with photovoltaic power supply considering multi- disturbance factor[J]. Southern Power System Technology, 2024, 18 (10): 130- 141.
9	LI K, LIN J Y, NIU F, et al. A novel fault leakage current detection method with protection deadzone elimination[J]. IEEE Transactions on Instrumentation and Measurement, 2020, 70, 3505009.
10	汪自虎, 王文天, 惠慧, 等. 基于近邻成分分析与优化核极限学习机的光伏接入配电网漏电识别[J]. 电高压电器, 2024, 60 (6): 0203- 02111.
	WANG Zhihu, WANG Wentian, HUI Hui, et al. Leakage recognition method of photovoltaic connected to distribution network based on neighborhood component analysis and optimized kernel extreme learning machine[J]. High Voltage Apparatus, 2024, 60 (6): 0203- 02111.
11	蔡智萍, 郭谋发, 魏正峰. 基于BP神经网络的低压配电网生命体触电识别方法研究[J]. 电网技术, 2022, 46 (4): 1614- 1623.
	CAI Zhiping, GUO Moufa, WEI Zhengfeng. Research on recognition method of living body shock in low-voltage distribution network based on BP neural network[J]. Power System Technology, 2022, 46 (4): 1614- 1623.
12	李春兰, 罗杰, 石砦, 等. 基于小波分析和概率神经网络的触电事故识别方法[J]. 江苏大学学报(自然科学版), 2023, 44 (1): 75- 81, 88.
	LI Chunlan, LUO Jie, SHI Zhai, et al. Electric shock identification method based on probabilistic neural network and wavelet analysis[J]. Journal of Jiangsu University (Natural Science Edition), 2023, 44 (1): 75- 81, 88.
13	徐寒, 朱三立, 张腾飞, 等. 低压配电系统剩余电流保护与重合闸逻辑组合优化方法[J]. 上海交通大学学报, 2025, 59 (7): 901- 911.
	XU Han, ZHU Sanli, ZHANG Tengfei, et al. Optimization method of residual current protection and coincidence brake logic combination of low voltage distribution system[J]. Journal of Shanghai Jiaotong University, 2025, 59 (7): 901- 911.
14	韩晓慧, 杜松怀, 苏娟, 等. 触电信号暂态特征提取及故障类型识别方法[J]. 电网技术, 2016, 40 (11): 3591- 3596.
	HAN Xiaohui, DU Songhuai, SU Juan, et al. Fault transient feature extraction and fault type identification for electrical shock signals[J]. Power System Technology, 2016, 40 (11): 3591- 3596.
15	李春兰, 罗杰, 王长云, 等. 基于循环谱特征和聚类分析的触电识别[J]. 电工技术学报, 2021, 36 (22): 4677- 4686.
	LI Chunlan, LUO Jie, WANG Changyun, et al. Electric shock recognition method based on cyclic spectrum features and cluster analysis[J]. Transactions of China Electrotechnical Society, 2021, 36 (22): 4677- 4686.
16	高伟, 饶俊民, 全圣鑫, 等. 不均衡小样本下多特征优化选择的生命体触电故障识别方法[J]. 电工技术学报, 2024, 4 (39): 2060- 2071.
	GAO Wei, RAO Junmin, QUAN Shengxin, et al. Biological electric-shock fault identification method based on multi-feature optimization selection under unbalanced small sample[J]. Transactions of China Electrotechnical Society, 2024, 4 (39): 2060- 2071.
17	刘斌, 吉春霖, 曹丽君, 等. 基于自适应噪声完全集合经验模态分解与BiLSTM-Transformer的锂离子电池剩余使用寿命预测[J]. 电力系统保护与控制, 2024, 52 (15): 167- 177.
	LIU Bin, JI Chunlin, CAO Lijun, et al. Prediction of remaining service life of lithium-ion batteries based on complete ensemble empirical mode decomposition with adaptive noise and BiLSTM-Transformer[J]. Power System Protection and Control, 2024, 52 (15): 167- 177.
18	刘友波, 吴浩, 刘挺坚, 等. 集成经验模态分解与深度学习的用户侧净负荷预测算法[J]. 电力系统自动化, 2021, 45 (24): 57- 64.
	LIU Youbo, WU Hao, LIU Tingjian, et al. User-side net load forecasting method integrating empirical mode decomposition and deep learning[J]. Automation of electric power systems, 2021, 45 (24): 57- 64.
19	GAO Z H, LIU Y, WANG Q J, et al. Ensemble empirical mode decomposition energy moment entropy and enhanced long short-term memory for early fault prediction of bearing[J]. Measurement, 2022, 188, 110417. DOI
20	SOWMYA R, PREMKUMAR M, JANGIR P. Newton-raphson-based optimizer: a new population-based metaheuristic algorithm for continuous optimization problems[J]. Engineering Applications of Artificial Intelligence, 2024, 128, 107532. DOI
21	CHEN T Q, GUESTRIN C. XGBoost: a scalable tree boosting system[C]//Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. San Francisco California USA. ACM, 2016: 785–794.
22	庄家懿, 杨国华, 郑豪丰, 等. 基于多模型融合的CNN-LSTM-XGBoost短期电力负荷预测方法[J]. 中国电力, 2021, 54 (5): 46- 55. DOI
	ZHUANG Jiayi, YANG Guohua, ZHENG Haofeng, et al. Short-term load forecasting method based on multi-model fusion using CNN-LSTM-XGBoost framework[J]. Electric Power, 2021, 54 (5): 46- 55. DOI
23	柯亮, 李波, 廖凯, 等. 基于XGBoost的配电网高阻接地故障检测方法[J]. 电力系统保护与控制, 2024, 52 (6): 88- 98.
	KE Liang, LI Bo, LIAO Kai, et al. High impedance fault detection method in a distribution network based on XGBoost[J]. Power System Protection and Control, 2024, 52 (6): 88- 98.
24	范兴明, 许洪华, 李涛, 等. 基于SMA-VMD 和能量熵的高压断路器故障诊断[J]. 高电压技术, 2024, 50 (12): 5248- 5258.
	FAN Xingming, XU Honghua, LI Tao, et al. Fault diagnosis of high-voltage circuit breakers based on SMA-VMD and energy entropy[J]. High Voltage Engineering, 2024, 50 (12): 5248- 5258.
25	刘永梅, 盛万兴, 杜松怀. 一种面向剩余电流保护装置的触电阻抗建模方法[J]. 河北工业大学学报, 2017, 46 (4): 15- 23.
	LIU Yongmei, SHENG Wanxing, DU Songhuai. An electric shock impedance modeling method of living organisms in low-voltage distribution network[J]. Journal of Hebei University of Technology, 2017, 46 (4): 15- 23.

模态分量	能量熵
模态分量	线路正常漏电	光伏漏电	三相不平衡漏电	生物体触电
IMF1	3.1×10^–7	8.3×10^–7	0.0017	0.0327
IMF2	7.9×10^–8	2.3×10^–7	0.0065	0.0092
IMF3	8.7×10^–7	3.4×10^–6	0.0186	0.0976
IMF4	7.7×10^–7	0.0061	0.0175	0.0923
IMF5	7.3×10^–7	0.0258	0.0170	0.0896
IMF6	7.2×10^–7	0.0037	0.0168	0.0878
IMF7	7.1×10^–7	0.0014	0.0195	0.0889
IMF8	6.2×10^–7	0.0027	0.0185	0.0878
IMF9	6.5×10^–7	0.0128	0.0181	0.1026
IMF10	8.4×10^–7	0.0048	0.0149	0.0998
IMF11	2.4×10^–5	0.0443	0.0268	0.0786
IMF12	0.0113	0.0008	0.0674	0.0706
IMF13	0.0151	0.0578	0.0379	0.1170
IMF14			0.2987	0.4561
IMF15			1.0029	10.2028

模态分量	能量熵
模态分量	线路正常漏电	光伏漏电	三相不平衡漏电	生物体触电
IMF1	3.1×10^–7	8.3×10^–7	0.0017	0.0327
IMF2	7.9×10^–8	2.3×10^–7	0.0065	0.0092
IMF3	8.7×10^–7	3.4×10^–6	0.0186	0.0976
IMF4	7.7×10^–7	0.0061	0.0175	0.0923
IMF5	7.3×10^–7	0.0258	0.0170	0.0896
IMF6	7.2×10^–7	0.0037	0.0168	0.0878
IMF7	7.1×10^–7	0.0014	0.0195	0.0889
IMF8	6.2×10^–7	0.0027	0.0185	0.0878
IMF9	6.5×10^–7	0.0128	0.0181	0.1026
IMF10	8.4×10^–7	0.0048	0.0149	0.0998
IMF11	2.4×10^–5	0.0443	0.0268	0.0786
IMF12	0.0113	0.0008	0.0674	0.0706
IMF13	0.0151	0.0578	0.0379	0.1170
IMF14			0.2987	0.4561
IMF15			1.0029	10.2028

算法	参数名称	参数值
NRBO	种群规模	20
	最大迭代次数	50
	搜索空间维度	3
	避免陷进决定因素	0.6
XGBoost	决策树深度	[1, 15]
	决策树数量	[10, 500]
	学习率	[0.0001, 0.3]
	子节点最小权重	1

算法	参数名称	参数值
NRBO	种群规模	20
	最大迭代次数	50
	搜索空间维度	3
	避免陷进决定因素	0.6
XGBoost	决策树深度	[1, 15]
	决策树数量	[10, 500]
	学习率	[0.0001, 0.3]
	子节点最小权重	1

模型	评价指标	状态1	状态2	状态3	状态4
XGBoost	准确率/%	92.5
	精确度/%	96.7	85.3	89.3	100.0
	召回率/%	96.7	96.7	83.3	93.3
	F1分数/%	96.7	90.6	86.2	96.5

NRBO- XGBoost	准确率/%	99.2
	精确度/%	100.0	100.0	96.8	100.0
	召回率/%	100.0	100.0	100.0	96.7
	F1分数/%	100.0	100.0	98.4	98.3