TY - JOUR
T1 - Electricity Theft Detection Using Euclidean and Graph Convolutional Neural Networks
AU - Liao, Wenlong
AU - Yang, Zhe
AU - Liu, Kuangpu
AU - Zhang, Bin
AU - Chen, Xinxin
AU - Song, RuNan
PY - 2023/7
Y1 - 2023/7
N2 - The widespread penetration of advanced metering infrastructure brings an opportunity to detect electricity theft by analyzing the electricity consumption data collected from smart meters. However, existing models have poor performance in electricity theft detection, since most of them fail to capture the time dependence, periodicity, and latent feature from complex electricity consumption data. To address above concerns, a graph convolutional neural network (GCN) and a Euclidean convolutional neural network (CNN) are combined to form a novel model for electricity theft detection in this paper. On one hand, the high-dimensional power load curves are modeled as a graph from a new perspective on graph theory. Then, the GCN depicts the time dependence and periodicity by performing graph convolutional operations. On the other hand, the CNN captures the latent features from the power load curves by carrying out Euclidean convolutional procedures. Numerical simulations show that the proposed model integrates the benefits of GCN and CNN, leading to superiority over the popular benchmarks in electricity theft detection.
AB - The widespread penetration of advanced metering infrastructure brings an opportunity to detect electricity theft by analyzing the electricity consumption data collected from smart meters. However, existing models have poor performance in electricity theft detection, since most of them fail to capture the time dependence, periodicity, and latent feature from complex electricity consumption data. To address above concerns, a graph convolutional neural network (GCN) and a Euclidean convolutional neural network (CNN) are combined to form a novel model for electricity theft detection in this paper. On one hand, the high-dimensional power load curves are modeled as a graph from a new perspective on graph theory. Then, the GCN depicts the time dependence and periodicity by performing graph convolutional operations. On the other hand, the CNN captures the latent features from the power load curves by carrying out Euclidean convolutional procedures. Numerical simulations show that the proposed model integrates the benefits of GCN and CNN, leading to superiority over the popular benchmarks in electricity theft detection.
KW - Analytical models
KW - Convolutional neural networks
KW - Correlation
KW - Data models
KW - Deep learning
KW - Electricity theft detection
KW - Feature extraction
KW - Graph convolutional neural network
KW - Load modeling
KW - Machine learning
KW - Smart grids
KW - Support vector machines
KW - machine learning
KW - deep learning
KW - smart grids
KW - graph convolutional neural network
UR - http://www.scopus.com/inward/record.url?scp=85135992594&partnerID=8YFLogxK
U2 - 10.1109/TPWRS.2022.3196403
DO - 10.1109/TPWRS.2022.3196403
M3 - Journal article
SN - 0885-8950
VL - 38
SP - 3514
EP - 3527
JO - I E E E Transactions on Power Systems
JF - I E E E Transactions on Power Systems
IS - 4
ER -