Anomaly Detection Method for Power Settlement Electricity Data Based on Graph Theory and Hybrid Convolutional Neural Network

Jie ZHANG, Langsen FANG, Liming YAO, Jinghui WU, Liu YANG, Jianquan ZHU

South Power Sys Technol ›› 2026, Vol. 20 ›› Issue (3) : 146-158.

PDF(2850 KB)
image
Home Journals Southern Power System Technology
Southern Power System Technology

Abbreviation (ISO4): South Power Sys Technol      Editor in chief:

About  /  Aim & scope  /  Editorial board  /  Indexed  /  Contact  / 
Online first  /  Current issue  /  All issues  /  Top access  /  RSS
PDF(2850 KB)
South Power Sys Technol ›› 2026, Vol. 20 ›› Issue (3) : 146-158. DOI: 10.13648/j.cnki.issn1674-0629.2026.03.014
Power Quality Analysis

Anomaly Detection Method for Power Settlement Electricity Data Based on Graph Theory and Hybrid Convolutional Neural Network

Author information +
History +

Abstract

In order to improve the efficiency and accuracy of electricity market settlement, an anomaly detection method is proposed for power settlement electricity data based on graph theory and hybrid convolutional neural network. Firstly, the input data is preprocessed using a hybrid resampling technique to solve the class imbalance problem in the data sets. Secondly, based on graph theory, the electricity data is transformed from a one-dimensional sequence structure to a two-dimensional graph structure, and the periodicity and temporal correlation characteristics of the graph structure are mined through graph convolutional network and convolutional neural network to improve the detection accuracy of abnormal electricity. Furthermore, a spatial attention mechanism is introduced into convolutional neural network to improve the detection performance of the model. Finally, abnormal data detection is performed on the actual power data sets. And the results show that the proposed method is superior in comprehensive performance such as accuracy and area under curve (AUC) value.

Key words

electricity data / anomaly data detection / convolutional neural network / deep learning / machine learning

Cite this article

EndNote

Ris (Procite)

Bibtex

Download Citations
Jie ZHANG , Langsen FANG , Liming YAO , et al . Anomaly Detection Method for Power Settlement Electricity Data Based on Graph Theory and Hybrid Convolutional Neural Network[J]. Southern Power System Technology. 2026, 20(3): 146-158 https://doi.org/10.13648/j.cnki.issn1674-0629.2026.03.014

References

List( Publishing order | Descend order by publishing year | Descend order by cited within ) Chart analysis
[1]
关立， 常江， 孙大雁， 等. 省间电力现货市场试运行分析及思考［J］. 电力系统自动化， 2024， 48（11）： 2 - 10.
GUAN Li， CHANG Jiang， SUN Dayan， et al. Analysis and reflection on trial operation of inter-provincial electricity spot markets in China［J］. Automation of Electric Power Systems， 2024， 48（11）： 2 - 10.
Cited in this article [1]
[2]
黄海涛， 顾颖， 叶云龙. 双轨制下新能源参与现货电能量市场的电力交易与结算方式［J］. 电力建设， 2024， 45（11）： 174 - 188.
HUANG Haitao， GU Ying， YE Yunlong. Electricity trading and settlement methods for renewable energy participation in the spot electricity market under the dual track system［J］. Electric Power Construction， 2024， 45（11）： 174 - 188.
[3]
李祥光， 谭青博， 李帆琪， 等. 电碳耦合对煤电机组现货市场结算电价影响分析模型［J］. 中国电力， 2024， 57（5）： 113 - 125.
LI Xiangguang， TAN Qingbo， LI Fanqi， et al. Analysis model to study the influence of electrocarbon coupling on settlement price of coal power units in spot market［J］. Electric Power， 2024， 57（5）： 113 - 125.
Cited in this article [1]
[4]
严明辉， 潘舒宸， 吴滇宁， 等. 基于非参数核密度估计的电力市场用户电量异常数据辨识与修正方法［J］. 现代电力， 2022， 39（1）： 80 - 87.
YAN Minghui， PAN Shuchen， WU Dianning， et al. An identification and correction method of abnormal data of electricity market consumers based on nonparametric kernel density estimation［J］. Modern Electric Power， 2022， 39（1）： 80 - 87.
Cited in this article [1]
[5]
YAN Z， WEN H. Performance analysis of electricity theft detection for the smart grid： an overview［J］. IEEE Transactions on Instrumentation and Measurement， 2021（71）： 2502928.
Cited in this article [1]
[6]
LEITE J B， MANTOVANI J R S. Detecting and locating non-technical losses in modern distribution networks［J］. IEEE Transactions on Smart Grid， 2018， 9（2）： 1023 - 1032.
Cited in this article [1]
[7]
XIE B， PENG C， YANG M， et al. A novel trust-based false data detection method for power systems under false data injection attacks［J］. Journal of the Franklin Institute， 2021， 358（1）： 56 - 73.
Cited in this article [1]
[8]
杨茂， 翟冠强， 苏欣. 基于风特征分析的风电机组异常数据识别算法［J］. 中国电机工程学报， 2017， 37（S1）： 144 - 151.
YANG Mao， ZHAI Guangiang， SU Xin. An algorithm for abnormal data identification of wind turbine based on wind characteristic analysis［J］. Proceedings of the CSEE， 2017， 37（S1）： 144 - 151.
Cited in this article [1]
[9]
JOKAR P， ARIANPOO N， LEUNG V C M. Electricity theft detection in AMI using customers’consumption patterns［J］. IEEE Transactions on Smart Grid， 2016， 7（1）： 216 - 226.
Cited in this article [2]
[10]
薛阳， 杨艺宁， 廖文龙， 等. 基于非线性独立成分估计的分布式光伏窃电数据增强方法［J］. 电力系统自动化， 2022， 46（2）： 171 - 179.
XUE Yang， YANG Yining， LIAO Wenlong， et al. Data augmentation method for distributed photovoltaic electricity theft based on non-linear independent components estimation［J］. Automation of Electric Power Systems， 2022， 46（2）： 171 - 179.
Cited in this article [1]
[11]
PEREIRA L A M， AFONSO L C S， PAPA J P. Multilayer perceptron neural networks training through charged system search and its Application for non-technical losses detection［C］//2013 IEEE PES Conference on Innovative Smart Grid Technologies （ISGT Latin America）， April 15 - 17， 2013， Sao Paulo， Brazil. New York： IEEE， 2013.
Cited in this article [2]
[12]
王庆宁， 张东辉， 孙香德. 基于GA-BP神经网络的反窃电系统研究与应用［J］. 电测与仪表， 2018， 55（11）： 35 - 40.
WANG Qingning， ZHANG Donghui， SUN Xiangde. Research and application of electricity anti-stealing system based on GA-BP neural network［J］. Electrical Measurement & Instrumentation， 2018， 55（11）： 35 - 40.
Cited in this article [1]
[13]
张爱梅. 基于不平衡电能数据的反窃电智能监测系统研究［J］. 电工技术， 2024（4）： 134 - 136.
ZHANG Aimei. Imbalanced-electricity-data-based intelligent monitoring system against electricity theft［J］. Electric Engineering， 2024（4）： 134 - 136.
Cited in this article [2]
[14]
周赣， 华济民， 李铭钧， 等. 基于图转换和混合卷积神经网络的窃电检测方法［J］. 电力系统自动化， 2022， 46（19）： 78 - 86.
ZHOU Gan， HUA Jimin， LI Mingjun， et al. Electricity theft detection method based on graph transformation and hybrid convolutional neural network［J］. Automation of Electric Power Systems， 2022， 46（19）： 78 - 86.
Cited in this article [1]
[15]
游文霞， 李清清， 杨楠， 等. 基于多异学习器融合Stacking集成学习的窃电检测［J］.电力系统自动化， 2022， 46（24）： 178 - 186.
YOU Wenxia， LI Qingqing， YANG Nan， et al. Electricity theft detection based on multiple different learner fusion by stacking ensemble learning［J］. Automation of Electric Power Systems， 2022， 46（24）： 178 - 186.
Cited in this article [2]
[16]
KHAN I U， JAVEID N， TAYLOR C J， et al. A stacked machine and deep learning-based approach for analysing electricity theft in smart grids［J］. IEEE Transactions on Smart Grid， 2022， 13（2）： 1633 - 1644.
Cited in this article [2]
[17]
BUZAU M M， TEJEDOR-AGUILERA J， CRUZ-ROMERO P， et al. Hybrid deep neural networks for detection of non-technical losses in electricity smart meters［J］. IEEE Transactions on Power Systems， 2020， 35（2）： 1254 - 1263.
Cited in this article [1]
[18]
黄光磊， 田启东， 林志贤， 等. 基于图卷积神经网络和格拉姆角场的电能质量扰动分类［J］. 电气传动， 2024， 54（3）： 84 - 90.
HUANG Guanglei， TIAN Qidong， LIN Zhixian， et al. Power quality disturbance classification based on graph convolutional neural networks and Gramian angular field［J］. Electric Drive， 2024， 54（3）： 84 - 90.
Cited in this article [1]
[19]
ZHENG Z B， YANG Y T， NIU X D， et al. Wide and deep convlutional neural networks for electricity-theft detection to secure smart grids［J］. IEEE Transactions on Industrial Informatics， 2018， 14（4）： 1606 - 1615.
Cited in this article [5]
[20]
何国立， 齐冬莲， 闫云凤. 一种基于关键点检测和注意力机制的违规着装识别算法及其应用［J］. 中国电机工程学报， 2022， 42（5）： 1826 - 1837.
HE Guoli， QI Donglian， YAN Yunfeng. An illegal dress recognition algorithm based on key-point detection and attention mechanism and its application［J］. Proceedings of the CSEE， 2022， 42（5）： 1826 - 1837.
Cited in this article [1]
[21]
王怀远， 陈启凡. 基于代价敏感堆叠变分自动编码器的暂态稳定评估方法［J］. 中国电机工程学报， 2020， 40（7）： 2213 - 2220，2400.
WANG Huaiyuan， CHEN Qifan. A transient stability assessment method based on cost-sensitive stacked variational auto-encoder［J］. Proceedings of the CSEE， 2020， 40（7）： 2213 - 2220，2400.
Cited in this article [1]
[22]
孙喆. 基于机器学习的电力用户窃电行为检测［D］. 北京： 华北电力大学， 2023.
Cited in this article [1]
[23]
张承智， 肖先勇， 郑子萱. 基于实值深度置信网络的用户侧窃电行为检测［J］.电网技术， 2019， 43（3）： 1083 - 1091.
ZHANG Chengzhi， XIAO Xianyong， ZHENG Zixuan. Electricity theft detection for customers in power utility based on real-valued deep belief network［J］. Power System Technology， 2019， 43（3）： 1083 - 1091.
Cited in this article [1]
[24]
FIGUEROA G， CHEN Y S， AVILA N， et al. Improved practices in machine learning algorithms for NTL detection with imbalanced data［C］//2017 IEEE Power & Energy Society General Meeting， July 16 - 20， 2017， Chicago， IL， USA. New York：IEEE， 2017.
Cited in this article [1]
[25]
张梦， 陈旭勇， 彭元林， 等. 基于改进合成少数类过采样技术的非概率可靠性指标解［J］. 武汉工程大学学报， 2024， 46（2）： 231 - 236.
ZHANG Meng， CHEN Xuyong， PENG Yuanlin， et al. Solution to non-probabilistic reliability indices based on improved synthetic minority oversampling technique［J］. Journal of Wuhan Institute of Technology， 2024， 46（2）： 231 - 236.
Cited in this article [1]
[26]
罗超月岭， 郑韵馨， 徐帧雨， 等. 基于Borderline-SMOTE-IHT混合采样的改进GWO-SVM变压器故障诊断方法［J］. 智慧电力， 2023， 51（7）： 108 - 114.
LUO Chaoyueling， ZHENG Yunxin， XU Zhenyu， et al. Improved GWO-SVM transformer fault diagnosis method based on Borderline-SMOTE-IHT mixed sampling［J］. Smart Power， 2023， 51（7）： 108 - 114.
Cited in this article [1]
[27]
SMITH M R， MARTINEZ T， GIRAUD-CARRIER C. An instance level analysis of data complexity［J］. Machine learning， 2014（95）： 225 - 256.
Cited in this article [1]
[28]
辛瑗. 面向海量数据的电力负荷可视化与分析预测方法研究［D］. 南京： 东南大学， 2022.
Cited in this article [1]
[29]
白云霄，许遵楠，季天瑶，等. 北欧电力衍生品市场对中国电力中长期市场建设的启示［J］. 南方电网技术，2025，19（8）：70 - 80.
BAI Yunxiao， XU Zunnan， JI Tianyao， et al. Inspiration of the nordic electricity derivatives market for the construction of China’s medium and long-term electricity market［J］. Southern Power System Technology，2025，19（8）：70 - 80.
Cited in this article [1]
[30]
刘菡， 王英男， 李新利， 等. 基于互信息-图卷积神经网络的燃煤电站NOx排放预测［J］. 中国电机工程学报， 2022， 42（3）： 1052 - 1060.
LIU Han， WANG Yingnan， LI Xinli， et al. Prediction of NOx emissions of coal-fired power plants based on mutual information-graph convolutional neural network［J］. Proceedings of the CSEE， 2022， 42（3）： 1052 - 1060.
Cited in this article [1]
[31]
廖文龙， 于贇， 王煜森， 等. 基于图卷积网络的配电网无功优化［J］ .电网技术， 2021， 45（6）： 2150 - 2160.
LIAO Wenlong， YU Yun， WANG Yusen， et al. Reactive power optimization of distribution network based on graph convolutional network［J］. Power System Technology， 2021， 45（6）： 2150 - 2160.
Cited in this article [1]
[32]
游文霞， 申坤， 杨楠， 等. 基于AdaBoost集成学习的窃电检测研究［J］. 电力系统保护与控制， 2020， 48（19）： 151 - 159.
YOU Wenxia， SHEN Kun， YANG Nan， et al. Research on electricity theft detection based on AdaBoost ensemble learning［J］. Power System Protection and Control， 2020， 48（19）： 151 - 159.
Cited in this article [1]

Funding

the National Natural Science Foundation of China(51977081)
the Innovation Project of Guangdong Electric Power Trading Center Co.,Ltd(GDKJXM20222721)
PDF(2850 KB)

Accesses

Citation

Detail
Sections
Recommended

/

〈 〉