Abstract: Aiming at several problems existing in the collected data reading of smart meters, combining dynamic initial value and metabolic modeling ideas, a method based on the improved GM（1,1） model for the reading and judgment of secondary out-account collected data reading of smart meters is proposed. Taking the data in the original data sequence as the initial value of the GM（1,1） model in turn, we infer the initial value corresponding to the smallest residual error, thereby, the data dimension required to minimize the residual error of the GM（1,1） model is obtained. And then, the metabolic modeling idea is used to establish an improved GM（1,1） model, and the model is applied to the secondary study and judgment of the collected data reading of the smart meter that failed in the first billing. The results show that, compared with the traditional least squares method and the traditional GM（1,1） model, the improved GM（1,1） model has better prediction accuracy, which is more suitable for the secondary out-account research and judgment of the collected data reading of the smart meter.