采用FCM聚类与改进SVR模型的窃电行为检测  

Electric larceny detectionusing FCM clustering and improved SVR model

作　　者：康宁宁 李川[1] 曾虎[1] 李英娜[1] 

机构地区：[1]昆明理工大学信息工程与自动化学院,昆明650504

出　　处：《电子测量与仪器学报》2017年第12期2023-2029,共7页Journal of Electronic Measurement and Instrumentation

摘　　要：针对窃电手段多样、隐蔽性强、窃电检测效率有待提高等问题,首先采用模糊C均值(FCM)聚类算法构造不同的用户负荷特征曲线,通过待测负荷曲线与相应特征曲线作对比初步确定疑似窃电用户;其次,采用粒子群算法优化的支持向量机回归模型对疑似窃电用户的用电行为进行检测。实验证明,所用方法缩小了窃电检测的范围、克服了窃电样本少的影响,改善了窃电检测的效率,并且窃电检测的均方误差和平均绝对误差分别提高了0.0051和0.034。Aiming atthe variety of electric larceny means, the efficiency of electric larceny detection remains improvement. Firstly, the fuzzy C mean clustering algorithm is used to construct different load characteristic curves of the user, and the suspiciouselectric larceny user is preliminarily determined by comparing the curves to be detected with the corresponding characteristic curve. Secondly, the particle swarm optimization support vector machine regression model is adopted to detect the behavior of suspected power stealing users. The experiments show that this method can reduce the range of electricity larcenydetection and overcome the influence of less electricity larcenysamples, improve the efficiency ofelectricity larcenydetection, and increasethe mean square error and average absolute error by 0. 0051 and 0. 034 respectively.

关 键 词：窃电检测 负荷曲线 FCM聚类分析 粒子群算法 支持向量机回归算法 

分 类 号：TM73[电气工程—电力系统及自动化] TP311[自动化与计算机技术—计算机软件与理论]