Electricity Theft Detection

This is a realistic electricity consumption dataset released by State Grid Corporation of China (http://www.sgcc.com.cn/). This dataset contains the electricity consumption data of 42,372 electricity customers within 1,035 days (from Jan. 1, 2014 to Oct. 31, 2016). Please download all the three zip files (data.zip, data.z01 and data.z02) and unzip them together.

For more details about this paper, please refer to our paper "Wide and Deep Convolutional Neural Networks for Electricity-Theft Detection to Secure Smart Grids" (https://ieeexplore.ieee.org/document/8233155/).

Cite

Please cite our paper when you use this dataset.

[Plain Text]

Zibin Zheng, Yatao Yang, Xiangdong Niu, Hong-Ning Dai, Yuren Zhou, "Wide and Deep Convolutional Neural Networks for Electricity-Theft Detection to Secure Smart Grids", IEEE Transactions on Industrial Informatics,vol. 14, no. 4, pp. 1606-1615, April 2018 Publication year: 2018

[Bibtex Entry]

@ARTICLE{ZZheng:TII2018, 
	author={Z. Zheng and Y. Yang and X. Niu and H. Dai and Y. Zhou}, 
	journal={IEEE Transactions on Industrial Informatics}, 
	title={Wide and Deep Convolutional Neural Networks for Electricity-Theft Detection to Secure Smart Grids}, 
	year={2018}, 
	volume={14}, 
	number={4}, 
	pages={1606-1615}, 
	keywords={data analysis;load flow;neural nets;power consumption;power engineering computing;power system security;smart power grids;wide CNN model;deep CNN model;smart grids;abnormal electricity consumption pattern;novel electricity-theft detection method;deep CNN component;normal electricity usage;power grids;information flows;energy flows;massive data availability;data analysis;1D electricity consumption data;electricity theft nonperiodicity identification;normal electricity usage periodicity identification;Smart grids;Anomaly detection;Correlation;Support vector machines;Meters;Sensors;Neural networks;Convolutional neural networks (CNNs);deep learning;electricity-theft detection;machine learning;smart grids}, 
	doi={10.1109/TII.2017.2785963}, 
	ISSN={1551-3203}, 
	month={April},
}