Sparse reconstruction of EMT based on compressed sensing and L regularization with the split Bregman method

Abnormal data detection method of energy consumption of green building power equipment based on LOF algorithm

“…According to the reconstruction error between the original data and the reconstructed data, the power consumption abnormal data points are detected. Liu et al [5] proposed an optimization scheme for energy consumption and life of smart watt-hour meters based on edge computing. The edge server is used to receive and upload smart watt-hour meter data, and the influence factors of energy consumption and life are extracted by convolutional neural network (CNN) at the edge, and the K-means clustering algorithm is used to predict the change of electricity consumption, so as to obtain the optimization model of energy consumption and life.…”