Algorithm Implementation of Non-Intrusive Load Monitoring Based on Load Core Feature Identification

As an important part of smart grid, non-intrusive load identification technology has broad application prospects. At present, most of the existing identification algorithms are highly advanced and require great computing power, which is not conducive to implementation on micro-hardware such as embedded systems. In this research, load core features were extracted from common electrical appliances to design a load identification algorithm, based on the characteristics of active power, reactive power and harmonic current at the moment of switching on and off, and in a short time after any action. Six electrical loads were tested and the result indicated that the algorithm proposed could recognize load operating status with relatively high accuracy.