An Non-Intrusive Load Event Detection Approach Based on CEEMDAN-WTD-F Test

An Non-Intrusive Load Event Detection Approach Based on CEEMDAN-WTD-F Test

To improve the perception of the switch state of the electrical equipment and realize the identification of the non-intrusive load switching process more accurately, a non-intrusive load event detection method based on the CEEMDAN-WTD-F test is proposed in this paper. Firstly, the adaptive median filter is used to reduce the noise fluctuation of power data of electric equipment and the discrete sequence derivative is used to reduce turn-on transition time for individual loads. Then, based on the principle of decomposition denoising and statistical testing, Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) and Wavelet Threshold De-noising (WTD) are used to process the input signal, and then the F test is used to determine whether an event occurs. Then, the proposed detection method is verified on the BLUED public data set, and a comparison experiment is carried out with the existing detection algorithm. The experimental results fully show that the proposed method has a lower missed detection rate and false detection rate than other detection algorithms, and the detection precision rate, recall rate, and F1 value are higher than 97%.