Improving energy efficiency management has be-come an important task for current electricity market participat-ing entities,and monitoring consumption of pivotal appliances plays an important role in many applications.This paper focuses on detecting whether a residence possesses a certain type of appliance based on their electricity consumption and the problem of class imbalance within deep learning model training for large power appliances with the state'ON'.We propose a data-driven deep learning approach with attention mechanism to de-tect residential appliances from low-resolution aggregate energy consumption data.Firstly,the historical consumption profile of each user is divided into a specific length and labeled with the status of an appliance to generate training and test samples.Then,a deep convolutional neural network model with attention mechanism is trained,and the trained model is utilized to classify the test samples.Meanwhile,we obtain appliance status in a residence based on classification of multiple samples.Finally,we propose a novel approach of data generation for class imbalance of appliance detection using generative adversarial networks.In order to guarantee the quality,we devise a mechanism of self-validation to ensure generated data approximating real distribution of minor class samples.Experiments are conducted on a low-frequency smart meter data set sampled once every 30 minutes,and the results show that the proposed model performs better than hidden Markov model based algorithms and has good application prospects.

Chunyu Deng;Kehe Wu;Binbin Wang

China Electric Power Research Institute,Beijing 100192,China;State Key Laboratory of Alternate Electrical Power System with Renewable Energy Sources,North China Electric Power University,Beijing 102206,China;Software College,Northeastern University,Shenyang 110169,China

中国电机工程学会电力与能源系统学报（英文版）

[1]Chunyu Deng;Kehe Wu;Binbin Wang-.Residential Appliance Detection Using Attention-based Deep Convolutional Neural Network)[J].中国电机工程学会电力与能源系统学报（英文版）,2022(02):621-633

Residential,Appliance,Detection,Using,Attention,Deep,Convolutional,Neural,Network,Improving,energy,efficiency,management,has,come,important,task,current,electricity,market,participat,entities,monitoring,consumption,pivotal,appliances,plays,role,many,applications,This,paper,focuses,detecting,whether,residence,possesses,certain,type,their,problem,imbalance,within,deep,learning,model,training,large,power,state,ON,We,data,driven,approach,attention,mechanism,residential,from,low,resolution,aggregate,Firstly,historical,profile,each,user,divided,into,specific,length,labeled,status,test,samples,Then,convolutional,neural,trained,utilized,classify,Meanwhile,obtain,classification,multiple,Finally,novel,generation,detection,using,generative,adversarial,networks,In,order,guarantee,quality,devise,self,validation,ensure,generated,approximating,real,distribution,minor,Experiments,are,conducted,frequency,smart,meter,set,sampled,once,every,minutes,results,show,that,proposed,performs,better,than,hidden,Markov,algorithms,good,prospects

0.616279