一种基于混合模型的配电网三相线损异常检测新方法

打开文本图片集

中图分类号：TM744+.1 文献标识码：A 文章编号：1001-5922（2025）10-0246-05

A new method for three-phase line loss anomaly detection in distribution network based on hybrid model

GUOLei¹，LI Xiaofei²， ZHANG Huan³， GUO Peng，HU Meilin5 （1.Beijing Guodentsu Network Technology Co.，Ltd.，Beijing 1Ooo85，China; 2.Beijing Tianyi Digital Technology Co.，Ltd.，Beijing1OoO70，China）

Abstract：Aimingatthe problem of insufficient detectionaccuracy causedby non-stationarydata，multi-variable couplingand hidden abnormal modes in abnormal detection of line loss in distribution network，this paper proposes a hybrid diagnosis framework thatcombines variational mode decomposition（VMD），dimensional attention mechanism long short-term memory network（DAMLSTM） and convolutional autoencoder.The experiment is based on theactualdataofacity‘slow-voltage distribution network throughouttheyear.Theresults show thattheRMSE index of the proposed method is 49.3 % lower than that of the mainstream models such as SVR，RF，GRU，LSTM and EMD-LSTM，and the R2 coefficient is increased by 30.1 % . The range of anomaly detection error is controlled within 0%～4% .The research provides a high-precision and interpretable intelligent diagnosis scheme for line loss managementof distribution network，which has application value for improving the economy and securityof power grid.

Key words：distribution network line loss;anomalydetection;variational modal decomposition;dimension attention mechanism;long short-term memory network

线损[1-3是指电力系统运行中热能引起的能量损失，是影响电力企业经济效益的主要因素。（剩余5156字）