基于多模型融合Stacking集成学习的异常用电检测方法研究

针对单一异常用电检测方法对于存在不平衡性的数据集检测效率普遍不高的问题,提出了一种基于多模型融合Stacking集成学习的异常用电检测方法。首先,以居民用电数据作为研究对象,分析用户在习惯上表现的不同特征,结合不平衡处理技术和分类预测算法进行研究;其次,为了提高模型的整体性能,采用量子遗传算法对集成学习模型中的参数做优化处理;最后,通过云南某地区用电数据集进行验证,证明所提模型相比单一学习模型检测的准确率有明显提升,对提升异常排查效率,降低电力公司的运营成本具有重要意义。

Research on Abnormal Electricity Detection Method Based on Multi-model by Stacking Ensemble Learning

Aiming at solving the problem that the efficiency of single abnormal power detection method is generally not high,an abnormal power detection method based on multi-model by Stacking ensemble learning is introduced.Firstly,taking the residential electricity data as the research object,and based on the analysis of different characteristics of users’habits,this paper studies the imbalance processing technology and classification prediction algorithm.Secondly,in order to improve the overall performance of the model,the quantum genetic algorithm is used to optimize the parameter in the ensemble learning model.Finally,through verifying a data set of electricity consumption in a certain area of Yunnan,it is proved that the accuracy of the proposed model is significantly improved compared with a single learning model,which is of great significance for improving the efficiency of abnormal detection and reducing the operating cost of power companies.