Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

A Novel Combined Data-Driven Approach for Electricity Theft Detection

Kedi Zheng, Qixin Chen, Yi Wang, Chongqing Kang, Qing Xia

TL;DR

The maximum information coefficient (MIC) can be used to precisely detect thefts that appear normal in shapes and the clustering technique by fast search and find of density peaks (CFSFDP) finds the abnormal users among thousands of load profiles, making it quite suitable for detecting electricity thefts with arbitrary shapes.

Abstract

The two-way flow of information and energy is an important feature of the Energy Internet. Data analytics is a powerful tool in the information flow that aims to solve practical problems using data mining techniques. As the problem of electricity thefts via tampering with smart meters continues to increase, the abnormal behaviors of thefts become more diversified and more difficult to detect. Thus, a data analytics method for detecting various types of electricity thefts is required. However, the existing methods either require a labeled dataset or additional system information which is difficult to obtain in reality or have poor detection accuracy. In this paper, we combine two novel data mining techniques to solve the problem. One technique is the Maximum Information Coefficient (MIC), which can find the correlations between the non-technical loss (NTL) and a certain electricity behavior of the consumer. MIC can be used to precisely detect thefts that appear normal in shapes. The other technique is the clustering technique by fast search and find of density peaks (CFSFDP). CFSFDP finds the abnormal users among thousands of load profiles, making it quite suitable for detecting electricity thefts with arbitrary shapes. Next, a framework for combining the advantages of the two techniques is proposed. Numerical experiments on the Irish smart meter dataset are conducted to show the good performance of the combined method.

A Novel Combined Data-Driven Approach for Electricity Theft Detection

TL;DR

The maximum information coefficient (MIC) can be used to precisely detect thefts that appear normal in shapes and the clustering technique by fast search and find of density peaks (CFSFDP) finds the abnormal users among thousands of load profiles, making it quite suitable for detecting electricity thefts with arbitrary shapes.

Abstract

The two-way flow of information and energy is an important feature of the Energy Internet. Data analytics is a powerful tool in the information flow that aims to solve practical problems using data mining techniques. As the problem of electricity thefts via tampering with smart meters continues to increase, the abnormal behaviors of thefts become more diversified and more difficult to detect. Thus, a data analytics method for detecting various types of electricity thefts is required. However, the existing methods either require a labeled dataset or additional system information which is difficult to obtain in reality or have poor detection accuracy. In this paper, we combine two novel data mining techniques to solve the problem. One technique is the Maximum Information Coefficient (MIC), which can find the correlations between the non-technical loss (NTL) and a certain electricity behavior of the consumer. MIC can be used to precisely detect thefts that appear normal in shapes. The other technique is the clustering technique by fast search and find of density peaks (CFSFDP). CFSFDP finds the abnormal users among thousands of load profiles, making it quite suitable for detecting electricity thefts with arbitrary shapes. Next, a framework for combining the advantages of the two techniques is proposed. Numerical experiments on the Irish smart meter dataset are conducted to show the good performance of the combined method.

Paper Structure

This paper contains 15 sections, 14 equations, 12 figures, 2 tables.

Table of Contents

  1. Introduction
  2. Problem Statement
  3. Observer Meters
  4. False Data Injection
  5. A State-based Method of Correlation
  6. Methodology and Detection Framework
  7. Maximum Information Coefficient
  8. CFSFDP-based Unsupervised Detection
  9. Combined Detecting Framework
  10. Numerical Experiments
  11. Dataset
  12. Comparisons and Evaluation Criteria
  13. Numerical Results
  14. Sensitivity Analysis
  15. Conclusion

Figures (12)

  • Figure 1: Observer meters for areas and smart meters for customers
  • Figure 2: An example of the FDI types
  • Figure 3: A real case of NTL and power consumption of the suspected user yijia2016anomaly
  • Figure 4: An example distribution of data points
  • Figure 5: Scatter plot of $(\rho_p,\delta_p)$ of the example data points
  • ...and 7 more figures