Nonintrusive on-site load-monitoring method with self-adaption

摘要

Nonintrusive load monitoring (NILM) is an effective way to measure the demand side of electricity consumption. An on-site NILM method in high-frequency acquisition mode was explored, which makes the entire process, including the construction of load-waveform decomposition and a short-term dynamic signature database, as well as continuous on-site load identification, automatic and executable in real time. First, a load decomposition model was established based on the additivity principle of load current to obtain the independent load waveform. According to the operational signatures of the load, there was no need to obtain prior data by conducting a preliminary experiment. The load type was judged by Bayesian classification model, and a dynamic load signature database was adaptively built for independent users. Based on the dynamic signature database, load identification was realized by optimization model, obtaining the electricity consumption of load in real time. The effectiveness of the method was verified by measuring electricity-consumption data. According to the experiment, the method can be automatically executed on-site to adapt to different users, and the dynamic signature database established improves the weak universality caused by establishing the database in advance. The fast optimization based on the signature database ensures the identification is efficient and accurate.