Research on the Data Processing Method of Missing Current Based on BP Neural Network

Electricity is an essential form of energy in daily life, industrial production, and national defense. As the Internet of Things technology becomes mature and famous, the data collection technology of the electric power data of users is rich. When the electric power data of user process is collected at a high frequency, not all valid data can be collected in each data acquisition cycle, and there is an accidental loss of data when the electric power data of users is collected. In order to solve the problem of data missing in collecting current data, this paper designs an estimation method of missing items when the current data of users is accidentally missing. The designed method uses BP neural network to estimate missing items. Since the collected data are allowed to have tolerances, this paper proposes an evaluation standard for the performance of the estimation method of accidental missing data when tolerances exist. Experiments show that the proposed method can be effectively used to estimate the accidental missing items of current data.