An online non-intrusive load monitoring method based on Hidden Markov model

Non-intrusive load monitoring (NILM) can decompose the total power consumption measured by the smart meter into the power consumed by the individual appliances, so as to achieve the purpose of saving energy. In this paper, an improved method of Daubechies9 (DB9) which is a discrete wavelet is proposed, which can effectively remove the noise of the low-frequency components. On this basis, an online NILM method based on Hidden Markov model (HMM) is proposed. The model of load switching can be built using apparent power of transient-state with this method. Besides, the improved forward algorithm which effectively suppressing the data underflow in load classification is proposed. The proposed methods are embedded in the smart meter and can increase the overall recognition rate of the load over 90% in the experiments which prove that they have good applicability.