Abstract
One of the common types of electricity theft occurs by tampering with smart meters (SMs) to pay less than the actual consumption. This paper proposes a convolutional neural network (CNN)-based method for detection and location of electricity theft (DLET) in smart distribution systems. The proposed method combines SMs and observer meters (OMs) data to reflect both spatial information of the grid bus connection and daily temporal data, simultaneously. The spatial information becomes the spatial axis and the daily data becomes the temporal axis of the input 2D image for the CNN. Furthermore, the spatial information of SMs and OMs is conserved by matching the kernel size of CNN with the spatial axis of the input image. The proposed method is evaluated by SimBench dataset, which includes bus connection and temporal data. As a result, the proposed method outperforms traditional methods for detection of electricity theft.
| Original language | English |
|---|---|
| Title of host publication | 2023 IEEE Power and Energy Society General Meeting, PESGM 2023 |
| Publisher | IEEE Computer Society |
| ISBN (Electronic) | 9781665464413 |
| DOIs | |
| Publication status | Published - 2023 |
| Event | 2023 IEEE Power and Energy Society General Meeting, PESGM 2023 - Orlando, United States Duration: 2023 Jul 16 → 2023 Jul 20 |
Publication series
| Name | IEEE Power and Energy Society General Meeting |
|---|---|
| Volume | 2023-July |
| ISSN (Print) | 1944-9925 |
| ISSN (Electronic) | 1944-9933 |
Conference
| Conference | 2023 IEEE Power and Energy Society General Meeting, PESGM 2023 |
|---|---|
| Country/Territory | United States |
| City | Orlando |
| Period | 23/7/16 → 23/7/20 |
Bibliographical note
Publisher Copyright:© 2023 IEEE.
All Science Journal Classification (ASJC) codes
- Energy Engineering and Power Technology
- Nuclear Energy and Engineering
- Renewable Energy, Sustainability and the Environment
- Electrical and Electronic Engineering
