Research And Implements Of Resident Abnormal Electricity Identification System

With the development of social economy and the popularization of electric power,the loss of power is more and more serious as the scale of power grid expands.Power loss is a serious problem for all power companies.The loss of electricity directly brings economic losses and affects the development of power companies.The power loss is divided into technical loss and non-technical loss.Technical loss is a resistance loss caused by internal components of power system.Non-technical loss refers to the loss that is not related to the technical loss in power system.It comes from the power loss caused by electricity users' theft and employees'dereliction of duty.Non-technical brought by the frequency of power loss seriously damaged the interests of users and enterprises.It is crucial for power users and power companies to reduce the non-technical losses caused by stealing electricity.The current approach is a combination of testing equipment and on-site testing for each power user,which costs a lot of operating costs and human resources.To find effective means of abnormal electricity identification is a popular research field in recent years.This paper puts forward an anomalous electricity use model based on multi-dimensional compound features of electricity users.The support vector machine,local outlier factor,correlation measurement based on the similar user power load,and correlation change rate measurement based on the most relevant users-these four algorithms are adopted to extract four-dimensional compound features of anomalous electricity use from the perspective of global anomaly,local anomaly,regional space,and time sequence.Next,the logistic regression(LR)model is trained based on the compound features.After training,the LR model is adopted as the final anomalous electricity use identification model.Analysis of the practical power load data of users suggests that the LR model combine respective advantages of the four-dimensional compound features.Detection of anomalies using the LR model is an effective approach,which can reliably and accurately identify residents' anomalous electricity use.From the accuracy rate,recall rate,precision rate and scores of F1,it can be seen that the LR model is significantly superior to SVM.Based on the abnormal electricity consumption model based on the multidimensional complex characteristics of the residents,a simulation system of resident's abnormal power consumption is implemented in this paper.On the basis of the abnormal electricity model of the multidimensional complex characteristics of the residents' power users,a simulation system for the resident abnormal use of electricity is realized in this paper.The system realizes the training data uploading,data preprocessing,abnormal electricity simulation,model training,model storage model,result display and other functions.For users who are suspected of using abnormal power,it can not only show the probability of abnormal electricity consumption but also show the user load curve.