基于XGBoost算法的配网台区低压跳闸概率预测

doi:10.11930/j.issn.1004-9649.201908140

摘要/Abstract

摘要： 针对配网台区在夏季频繁出现低压跳闸故障的问题，提出基于机器学习的台区低压跳闸预警模型。首先，采用孤立森林和改进的合成少数类过采样技术（synthetic minority oversampling technique-nominal continuous，SMOTE-NC）算法的组合方法进行数据处理，在实现离群值分离的基础上，对包含多种数值类型的故障样本进行过采样，以解决样本不平衡问题。其次，利用优化的数据集训练极端梯度提升算法（extreme gradient boosting，XGBoost）分类器模型，对目标台区的低压跳闸故障概率进行预测。最后，以广州某地区的实测数据对算法的有效性进行验证，结果显示所提模型具有良好的应用效果。

关键词: 配网台区, 低压跳闸, 机器学习, 不平衡数据集, XGBoost

Abstract: In view of the frequent low-voltage tripping faults in the distribution transformer station areas during summer season, a machine learning-based warning model is proposed for low-voltage tripping in this paper. Firstly, a combination method based on isolated forest and synthetic minority oversampling technique-nominal continuous (SMOTE-NC) algorithm is proposed in data pre-processing phase. The aim of this combination method is to oversample the representative trip fault samples to adjust imbalance rate of dataset based on outlier separation. Secondly, the extreme gradient boosting (XGBoost) classifier model is trained using the optimized data sets to predict the probability of low-voltage tripping faults in the target station area. Finally, the proposed algorithm is validated by the measured data in an area of Guangzhou, and the results show it has good application effects.

Key words: distribution transformer station area, low-voltage tripping fault, machine learning, imbalanced dataset, XGBoost

吴琼, 余文铖, 洪海生, 喻蕾, 段炼, 尚明远, 刘哲. 基于XGBoost算法的配网台区低压跳闸概率预测[J]. 中国电力, 2020, 53(4): 105-113.

WU Qiong, YU Wencheng, HONG Haisheng, YU Lei, DUAN Lian, SHANG Mingyuan, LIU Zhe. Probability Prediction of Low-voltage Tripping Failures in Distribution Transformer Station Areas Based on XGBoost Algorithm[J]. Electric Power, 2020, 53(4): 105-113.

导出引用管理器 EndNote|Ris|BibTeX

链接本文: https://www.electricpower.com.cn/CN/10.11930/j.issn.1004-9649.201908140

https://www.electricpower.com.cn/CN/Y2020/V53/I4/105

参考文献

[1] 冷华, 童莹, 李欣然, 等. 配电网运行状态综合评估方法研究[J]. 电力系统保护与控制, 2017, 45(1): 53–59
LENG Hua, TONG Ying, LI Xinran, et al. Comprehensive evaluation method research of the operation state in distributed network[J]. Power System Protection and Control, 2017, 45(1): 53–59
[2] 李博, 高志远. 人工智能技术在智能电网中的应用分析和展望[J]. 中国电力, 2017, 50(12): 136–140
LI Bo, GAO Zhiyuan. Analysis and prospect on the application of artificial intelligence technologies in smart grid[J]. Electric Power, 2017, 50(12): 136–140
[3] 余贻鑫. 智能电网实施的紧迫性和长期性[J]. 电力系统保护与控制, 2019, 47(17): 1–5
YU Yixin. Urgency and long-term nature of smart grid implementation[J]. Power System Protection and Control, 2019, 47(17): 1–5
[4] 王鹏, 陈旦, 周霞. 中国2017年度供电可靠性现状分析与展望[J]. 中国电力, 2018, 51(8): 1–9, 138
WANG Peng, CHEN Dan, ZHOU Xia. Analysis and prospect of power supply reliability in China in 2017[J]. Electric Power, 2018, 51(8): 1–9, 138
[5] 贺建章, 王海波, 季知祥, 等. 面向智能电网的配电变压器重过载影响因素分析[J]. 电网技术, 2017, 41(1): 279–284
HE Jianzhang, WANG Haibo, JI Zhixiang, et al. Analysis of factors affecting distribution transformer overload in smart grid[J]. Power System Technology, 2017, 41(1): 279–284
[6] 贺建章, 王海波, 季知祥, 等. 基于随机森林理论的配电变压器重过载预测[J]. 电网技术, 2017, 41(8): 2593–2597
HE Jianzhang, WANG Haibo, JI Zhixiang, et al. Heavy overload forecasting of distribution transformers based on random forest theory[J]. Power System Technology, 2017, 41(8): 2593–2597
[7] 张世良. 大数据背景下基于信赖域Logistic模型的短期配变重过载预警研究[C]// 中国电力科学研究院有限公司.第二届智能电网会议论文集. 北京: 国网电投 (北京) 科技中心, 2018: 315−322.
[8] 史常凯, 闫文棋, 张筱慧, 等. 基于BP网络和灰色模型的春节配变重过载预测[J]. 电力科学与技术学报, 2016, 31(3): 140–145
SHI Changkai, YAN Wenqi, ZHANG Xiaohui, et al. Heavy overload forecasting of distribution transformer during the spring festival based on BP network and grey model[J]. Journal of Electric Power Science and Technology, 2016, 31(3): 140–145
[9] 魏剑啸, 粟忠来, 杨波, 等. 配电台区无功功率及三相不平衡电容调节的研究[J]. 电力系统保护与控制, 2019, 47(16): 71–79
WEI Jianxiao, SU Zhonglai, YANG Bo, et al. Study on reactive power and three-phase unbalance regulated by capacitor in distribution network[J]. Power System Protection and Control, 2019, 47(16): 71–79
[10] 黄建明, 李晓明, 瞿合祚, 等. 考虑小波奇异信息与不平衡数据集的输电线路故障识别方法[J]. 中国电机工程学报, 2017, 37(11): 3099–3107, 3365
HUANG Jianming, LI Xiaoming, QU Hezuo, et al. Method for fault type identification of transmission line considering wavelet singular information and unbalanced dataset[J]. Proceedings of the CSEE, 2017, 37(11): 3099–3107, 3365
[11] 陈奎, 韦晓广, 陈景波, 等. 基于样本数据处理和ADABOOST的小电流接地故障选线[J]. 中国电机工程学报, 2014, 34(34): 6228–6237
CHEN Kui, WEI Xiaoguang, CHEN Jingbo, et al. Fault line detection using sampled data processing and ADABOOST for small current grounding system[J]. Proceedings of the CSEE, 2014, 34(34): 6228–6237
[12] 陈振, 肖先勇, 李长松, 等. 基于代价敏感极端学习机的电力系统暂态稳定评估方法[J]. 电力自动化设备, 2016, 36(2): 118–123
CHEN Zhen, XIAO Xianyong, LI Changsong, et al. Power system transient stability assessment based on cost-sensitive extreme learning machine[J]. Electric Power Automation Equipment, 2016, 36(2): 118–123
[13] 焦盛岚, 杨炳儒, 翟云, 等. 一种用于非平衡数据分类的集成学习模型[J]. 计算机工程与应用, 2012, 48(29): 119–123, 219
JIAO Shenglan, YANG Bingru, ZHAI Yun, et al. Ensemble learning model for imbalanced data classification[J]. Computer Engineering and Applications, 2012, 48(29): 119–123, 219
[14] GUO H, LI Y, SHANG J, et al. Learning from class-imbalanced data: review of methods and applications[J]. Expert Systems With Applications, 2017, 73: 220–239.
[15] 谢文旺, 孙云莲, 黄雅鑫. 基于改进随机森林的电力线通信优化算法研究[J]. 电力系统保护与控制, 2019, 47(11): 22–29
XIE Wenwang, SUN Yunlian, HUANG Yaxin. Research on power line communication optimization algorithm based on improved random forest[J]. Power System Protection and Control, 2019, 47(11): 22–29
[16] CHAWLA N V, BOWYER K W, HALL L O, et al. SMOTE: synthetic minority over-sampling technique[J]. Journal of Artificial Intelligence Research, 2002, 16: 321–357.
[17] 严英杰, 盛戈皞, 刘亚东, 等. 基于滑动窗口和聚类算法的变压器状态异常检测[J]. 高电压技术, 2016, 42(12): 4020–4025
YAN Yingjie, SHENG Gehao, LIU Yadong, et al. Anomalous state detection of power transformer based on algorithm sliding windows and clustering[J]. High Voltage Engineering, 2016, 42(12): 4020–4025
[18] 王雷, 张瑞青, 盛伟, 等. 基于支持向量机的回归预测和异常数据检测[J]. 中国电机工程学报, 2009, 29(8): 92–96
WANG Lei, ZHANG Ruiqing, SHENG Wei, et al. Regression forecast and abnormal data detection based on support vector regression[J]. Proceedings of the CSEE, 2009, 29(8): 92–96
[19] 刘沅昆, 栾文鹏, 徐岩, 等. 针对配电变压器的数据清洗方法[J]. 电网技术, 2017, 41(3): 1008–1014
LIU Yuankun, LUAN Wenpeng, XU Yan, et al. Data cleaning method for distribution transformer[J]. Power System Technology, 2017, 41(3): 1008–1014
[20] 赵庆周, 李勇, 田世明, 等. 基于智能配电网大数据分析的状态监测与故障处理方法[J]. 电网技术, 2016, 40(3): 774–780
ZHAO Qingzhou, LI Yong, TIAN Shiming, et al. A state estimation and fault processing method based on big data analysis of smart distribution network[J]. Power System Technology, 2016, 40(3): 774–780
[21] LIU F T, TING K M, ZHOU Z H. Isolation forest[C]//2008 Eighth IEEE International Conference on Data Mining, December 15-19, 2008. Pisa, Italy. IEEE, 2008: 413–422.
[22] XU D, WANG Y J, MENG Y L, et al. An improved data anomaly detection method based on isolation forest[C]//2017 10th International Symposium on Computational Intelligence and Design (ISCID), December 9-10, 2017. Hangzhou. IEEE, 2017: 287–291
[23] 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-KDD '16, August 13-17, 2016. San Francisco, California, USA. New York, USA: ACM Press, 2016.
[24] FRIEDMAN J H. Greedy function approximation: a gradient boosting machine[J]. Annals of Statistics, 2001, 29(5): 1189–1232.
[25] 赵洪山, 闫西慧, 王桂兰, 等. 应用深度自编码网络和XGBoost的风电机组发电机故障诊断[J]. 电力系统自动化, 2019, 43(1): 81–90
ZHAO Hongshan, YAN Xihui, WANG Guilan, et al. Fault diagnosis of wind turbine generator based on deep autoencoder network and XGBoost[J]. Automation of Electric Power Systems, 2019, 43(1): 81–90
[26] SUSTO G A, BEGHI A, MCLOONE S. Anomaly detection through on-line isolation forest: an application to plasma etching[C]//2017 40th International Convention on Information and Communication Technology, Electronics and Microelectronics (MIPRO), May 22-26, 2017. Opatija, Croatia. IEEE, 2017
[27] XIA Y F, LIU C Z, LI Y Y, et al. A boosted decision tree approach using Bayesian hyper-parameter optimization for credit scoring[J]. Expert Systems With Applications, 2017, 78: 225–241.