Measurement Error Estimation for Distributed Smart Meters Through a Modified BP Neural Network

Abstract

Smart meters generally suffer degradation of metering accuracy and performance due to aging, faults, and other factors, which, however, are difficult to detect. This study proposes a measurement error estimation method for distributed smart meters based on a modified BP neural network. First, the relationship model between the metering correction coefficient, network loss, and energy consumption measurement value for the distributed system is established. Then, a modified BP neural network for the parameter estimation method is proposed, in which the internal activation function, iterative step size, and other parameters are comprehensively designed. Finally, the parameters of the distributed smart meter measurement error are solved through training and learning. The case study verifies the effectiveness of the proposed method, and this study lays a theoretical foundation for accurate prediction of the measurement error for distributed smart meters.