基于用电特性分析的充电桩电价执行异常识别方法OACSTPCD

With the increasingly prominent issues of global warming and environmental pollution,new energy vehicles have gradually become an inevitable trend in the development of the automotive industry. Due to the low setting of charging prices for new energy electric vehicles,many charging stations have defaulted on electricity usage due to "high prices and low connections". Using mutual information algorithm to extract effective behavioral characteristics indicators of charging station users,combined with principal component analysis and KNN classification algorithm,an intelligent recognition model for abnormal electricity price execution of charging stations is constructed,which quickly and accurately locates defaulting electricity users,greatly improving the efficiency of inspection work. By analyzing examples and comparing multiple evaluation indicators such as precision,recall,F1 value,ROC curve,AUC value,etc.,the effectiveness of the model is verified.