测绘学报(英文版) ›› 2022, Vol. 5 ›› Issue (2): 29-37.doi: 10.11947/j.JGGS.2022.0204

• • 上一篇    下一篇

  

  • 收稿日期:2021-10-31 接受日期:2022-02-22 出版日期:2022-06-20 发布日期:2022-07-22

Estimating the Spatial Variation of Electricity Consumption Anomalies and the Influencing Factors

Yuyun LIANG(),Yao YAO(),Xiaoqin YAN,Qingfeng GUAN   

  1. School of Geography and Information Engineering, China University of Geosciences, Wuhan 430078, China
  • Received:2021-10-31 Accepted:2022-02-22 Online:2022-06-20 Published:2022-07-22
  • Contact: Yao YAO E-mail:20161000196@cug.edu.cn;yaoy@cug.edu.cn
  • About author:Yuyun LIANG, E-mail: 20161000196@cug.edu.cn
  • Supported by:
    National Natural Science Foundation of China(41801306);National Natural Science Foundation of China(42171466));The Scientific Research Program of the Department of Natural Resources of Hubei Province(ZRZY2021KJ02)

Abstract:

Effective detection of abnormal electricity users and analysis of the spatial distribution and influencing factors of abnormal electricity consumption in urban areas have positive effects on the quality of electricity consumption by customers, safe operation of power grids, and sustainable development of cities. However, current abnormal electricity consumption detection models do not consider the time dependence of time-series data and rely on a large number of training samples, and no study has analyzed the spatial distribution and influencing factors of abnormal electricity consumption in urban areas. In this study, we use the Seasonal-Trend decomposition procedure based on Loess (STL) based time series decomposition and outlier detection to detect abnormal electricity consumption in the central city of Pingxiang, and analyze the relationship between spatial variation and urban functions through Geodetector. The results show that the degree of abnormal electricity consumption in urban areas is related to geographic location and has spatial heterogeneity, and the abnormal electricity users are mainly located in areas with highly mixed residential, commercial and entertainment functions in the city. The results obtained from this study can provide a reference basis and a theoretical foundation for the detection of abnormal electricity consumption by users and the arming of electricity theft devices in the power grid.

Key words: abnormal electricity user detection, spatial autocorrelation, abnormal electricity usage in urban areas, points of interest enrichment factor, Geodetector