Abstract：This study aims to effectively identify abnormal or non-compliant electricity consumption behaviors in electric vehicle charging stations, thereby enhancing the efficiency and accuracy of electricity management for these stations. Initially, the study analyzes the electricity consumption behavior characteristics of low-voltage charging stations, determining the differences in load characteristic curves between normal and abnormal electricity consumption states. Based on this, a clustering analysis algorithm is employed to extract load curve characteristics from operational charging stations and compare them with standard load curves to assess the presence of abnormal electricity consumption behaviors. Additionally, considering potential misjudgments arising from the “fast charging” and “slow charging” phases during the charging process, the concept of sliding difference linear fitting is introduced. This involves calculating the slope between each pair of 96-point load data points and using the number of slope changes to assist in the judgment of clustering analysis results. Through the aforementioned methods, users exhibiting abnormal electricity consumption behaviors have been successfully identified, providing technical support for the management of electricity consumption in charging stations.
2025, Vol. 26 
