Journal of East China Normal University(Natural Science) ›› 2021, Vol. 2021 ›› Issue (5): 104-114.doi: 10.3969/j.issn.1000-5641.2021.05.010

• Data Analysis and Applications • Previous Articles     Next Articles

Electricity theft detection based on t-LeNet and time series classification

Xiaoqin MA1(), Xiaohui XUE1, Hongjiao LUO1, Tongyu LIU2, Peisen YUAN2,*()   

  1. 1. Information and Communication Company, State Grid Qinghai Province Electric Power Company, Xining 810008 China
    2. College of Artificial Intelligence, Nanjing Agricultural University, Nanjing 210095, China
  • Received:2021-08-07 Online:2021-09-25 Published:2021-09-28
  • Contact: Peisen YUAN;


Electricity theft results in significant losses in both electric energy and economic benefits for electric power enterprises. This paper proposes a method to detect electricity theft based on t-LeNet and time series classification. First, a user’s power consumption time series data is obtained, and down-sampling is used to generate a training set. A t-LeNet neural network can then be used to train and predict classification results for determining whether the user exhibits behavior reflective of electricity theft. Lastly, real user power consumption data from the state grid can be used to conduct experiments. The results show that compared with the time series classification method based on Time-CNN (Time Convolutional Neural Network) and MLP (Muti-Layer Perception), the proposed method offers improvements in the comprehensive evaluation index, accuracy rate, and recall rate index. Hence, the proposed method can successfully detect electricity theft.

Key words: time series classification, t-LeNet, electricity theft detection

CLC Number: