In modern society, the utilization rate of new energy vehicles is getting higher and higher. Many cities begin to promote new energy vehicles. The government also begins to attach importance to the development of new energy vehicles. Therefore, it is necessary for the entire distribution network to predict the load of the short-term new energy vehicle charging station. In this paper, a model based on the Complete Ensemble Empirical Mode Decomposition with Adaptive Noise(CEEMDAN) and Quantum Genetic Algorithm(QGA) -Elman is proposed to perform load forecasting on similar days new energy vehicle charging stations. Taking the historical data of similar days given by the new energy vehicle charging station as input parameters, the model is established to predict the load of the next day. The combination model is improved in reducing prediction errors, and the research problems have certain application value.