A Fault Diagnosis Method for Smart Meters via Two-layer Stacking Ensemble Optimization and Data Augmentation

作     者：Leijiao Ge Tianshuo Du Zhengyang Xu Luyang Hou Jun Yan Yuanliang Li 

作者机构：School of Electrical and Information EngineeringTianjin UniversityTianjin 300072China School of Computer Science(National Pilot Software Engineering School)Beijing University of Posts and TelecommunicationsBeijing 100876China Concordia Institute for Information Systems EngineeringConcordia UniversityMontrealQC H3G 1M8Canada 

出 版 物：《Journal of Modern Power Systems and Clean Energy》 (现代电力系统与清洁能源学报（英文）)

年 卷 期：2024年第12卷第4期

页      面：1272-1284页

核心收录：

学科分类：02[经济学] 0808[工学-电气工程] 0809[工学-电子科学与技术（可授工学、理学学位）] 0831[工学-生物医学工程（可授工学、理学、医学学位）] 0810[工学-信息与通信工程] 1205[管理学-图书情报与档案管理] 0202[经济学-应用经济学] 020205[经济学-产业经济学] 081203[工学-计算机应用技术] 0804[工学-仪器科学与技术] 0835[工学-软件工程] 0701[理学-数学] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：supported by the National Key R&D Program of China(No.2022YFB2403800) the National Natural Science Foundation of China(No.52277118) the Natural Science Foundation of Tianjin(No.22JCZDJC00660) the Open Fund in the State Key Laboratory of Alternate Electrical Power System With Renewable Energy Sources(No.LAPS23018) 

主　　题：Data augmentation fault diagnosis feature extraction smart meter Stacking ensemble optimization 

摘      要：The accurate identification of smart meter(SM)fault types is crucial for enhancing the efficiency of operationand maintenance(O&M)and the reliability of power ***,the intelligent classification of SM fault typesfaces significant challenges owing to the complexity of featuresand the imbalance between fault *** address these issues,this study presents a fault diagnosis method for SM incorporatingthree distinct *** first module employs acombination of standardization,data imputation,and featureextraction to enhance the data quality,thereby facilitating improvedtraining and learning by the *** enhance theclassification performance,the data imputation method considersfeature correlation measurement and sequential imputation,and the feature extractor utilizes the discriminative enhancedsparse *** tackle the interclass imbalance of datawith discrete and continuous features,the second module introducesan assisted classifier generative adversarial network,which includes a discrete feature generation ***,anovel Stacking ensemble classifier for SM fault diagnosis is *** contrast to previous studies,we construct a two-layerheuristic optimization framework to address the synchronousdynamic optimization problem of the combinations and hyperparametersof the Stacking ensemble classifier,enabling betterhandling of complex classification tasks using SM *** proposedfault diagnosis method for SM via two-layer stacking ensembleoptimization and data augmentation is trained and validatedusing SM fault data collected from 2010 to 2018 in Zhejiang Province,*** results demonstrate the effectivenessof the proposed method in improving the accuracyof SM fault diagnosis,particularly for minority classes.