Non-Intrusive Residential Load Decomposition Method Based on Steady State Feature Extraction

As an important part of intelligent power technology, non-intrusive residential load monitoring technology has gradually become an important research direction of intelligent power technology because it can obtain specifically detailed load monitoring data and further analyze the load components of residential users. At present, the transient characteristics are employed to analysis, which has high accuracy requirements for data acquisition equipment, so it is difficultly applied to practical problem. This paper proposes a non-intrusive household load decomposition method based on the identification of working modes of electrical appliances. Firstly, the steady-state characteristics of current waveform, active power and reactive power of household appliances are extracted. Then, a new method is proposed to determine the working mode of electrical appliances. In addition, the artificial neural network is employed to recognize the working mode of electrical appliances, and the load of household appliances is decomposed accurately. Finally, the simulation results show that the proposed method can effectively identify household appliances and decompose electrical load according to the steady-state characteristics.