Smart meter data

Load identification have shown significant performance gains in Chinese smart grids. Most existing load identification algorithms are based on electrical characteristics of steady or transient state, which are therefore limited by feature selection and analyzing pattern. To address above issues, this paper proposes the use of deep neural network for load identification in a Non-Intrusive Load Monitoring (NILM) test-bed, which is set up by introducing diversified household appliances with different load characteristics, to collect the real-time power usage of appliances in a typical Chinese home. The collected load data set are then sampled, preprocessed and input to the CNN-LSTM framework for training and features extraction. Next, according to serval experiments, the structure of our CNN-LSTM network is determined with reasonable hyper-parameters initialized. Numerical results show that our model is superior to the k-NN, SVM, LSTM and CNN load identification methods, with an average recognition accuracy of over 99\%, across different kinds of appliances enabled in the typical power grid in China.