Metering equipment running error estimation model based on genetic optimized LM algorithm

Abstract

The current method of smart meter verification relies on manual regular sampling inspection, which is heavy in workload and poor in real-time, and can’t fully monitor all the equipments. Therefore, a remote real-time error monitoring algorithm is indispensable. We propose a smart meter error estimation model based on genetic optimized Levenberg-Marquarelt (LM) algorithm. Firstly, based on the law of conservation of energy, the relationship between smart meter error and electricity consumption is established. Then, LM algorithm is optimized based on genetic algorithm and used to estimate the operating error of electricity meter. Finally, we used the actual data of the pilot cities in a province for the experiment. The results show that the proposed method can effectively improve the accuracy of smart meter error estimation.