A method for identifying and evaluating energy meter data based on big data analysis technology

Abstract

: In order to explore the measurement performance of grid energy meters under multi-dimensional influence conditions on site and map their measurement errors under standard laboratory conditions, a measurement error estimation method for on-site service energy meters based on big data analysis technology is proposed, which combines environmental data and electrical factor data from on-site operation to achieve online measurement error estimation. To address the problem of electricity meter demand prediction, a reasonable optimisation allocation model for electricity meters based on Shapley combination model and neural network is established to improve the accuracy of demand prediction. By mining historical data, Holt Winters, BP neural network, and RBF neural network models are used to predict, compare, and analyse the demand for electricity meters. The test results indicate that the built model can achieve reliability evaluation based on the real-time operating status of intelligent energy meters, providing auxiliary decision-making for the operation and maintenance of intelligent energy meters.