Household appliance classification using lower odd-numbered harmonics and the bagging decision tree

Abstract

Non-Intrusive Load Monitoring (NILM) systems have gained popularity in recent years for saving more energy. To reduce sensing infrastructure costs, NILM monitors the electrical loads based on a machine learning method. We propose a novel approach to improve the performance of classifying household appliances at a high sampling rate called FFT-BDT. The proposed method includes two main processes. The first process is generating novel features in the feature extraction stage. These features are the magnitude and phase (MP) at lower odd-numbered harmonics based on the Fast Fourier Transform (FFT). MP features are steady-state features at high frequency and used as input for a learning model. The second process is where a machine learning model, a bagging decision tree (BDT), learns the novel MP features. The proposed method enhances the accuracy of recognizing different appliances that have similar power consumption. To evaluate the FFT-BDT, we experimented on two NILM datasets, including the public PLAID dataset and our own private dataset. The method outperformed prior methods and could significantly contribute to load identification in NILM.