A Non-Intrusive Load Monitoring Method Based on Multi-scale Wavelet Packet Optimization and Transient Feature Matching

摘要

Non-intrusive load monitoring(NILM) is one of the key contents of intelligent power technology system, which can obtain the information of independent electrical appliances. In order to improve the accuracy of load identification, a transient load feature library based on active power is established and a multi-scale wavelet packet optimization NILM method is proposed. Firstly, optimal wavelet basis function is determined by wavelet packet energy entropy, Multi-scale wavelet packet transform is used to map the transient load feature library into wavelet domain energy space and form the standardized template. Load identification is analyzed according to the matching degree between the acquisition signal and the standardized template. The method is both simple and practical. Simulation results show this method can resolve feature overlapping problem effectively. The robustness and load identification rate of the algorithm are improved.