基于距离离群点数据挖掘技术的防窃电算法研究

Research on Anti-stealing Electricity Algorithm Based on Distance Outlier Data Mining Technology

为降低传统窃电检测方法存在的误报率和漏报率,简化数据分析算法以达到高效准确的检测效果,从而为现场稽查人员提供可靠的数据依据,在对窃电的方法和种类进行深入研究的基础上,设计一种基于距离的数据挖掘防窃电优化算法模型。该算法模型采用数据变换后的一维数据算法,依据电量波动率和距离离群点完成用户数据挖掘,准确识别窃电用户。最后通过现场采集数据,搭建仿真系统证明该算法辨别窃电用户准确率达90%以上,准确率比传统窃电算法提高10%以上,应用本算法大幅提高了现场检测人员的工作效率。

In order to reduce the false positive rate and missing report rate of the traditional detection method of stealing electricity,the data analysis algorithm to achieve efficient and accurate detection effect is simplified so as to provide reliable data basis for on-site inspectors.In this paper,a distance based data mining optimization algorithm model is designed based on the in-depth study of the methods and types of electricity stealing.The algorithm model uses one-dimensional data algorithm after data transformation to complete user data mining according to electricity fluctuation rate and distance outliers,and accurately identify power stealing users.Finally,through the field data collection,the simulation system shows that the accuracy rate of the algorithm is more than 90%,and the accuracy rate is at least 10%higher than the traditional power stealing algorithm.The application of this algorithm greatly improves the work efficiency of the field detection personnel.