In order to solve the problem of load fluctuation and stability in the distribution network caused by disorderly charging of electric vehicles in residential areas, this study proposes a residential area electric vehicle charging scheduling strategy based on Gaussian regression load prediction. By analyzing the real data of a certain residential area, the user’s electricity and car usage habits are obtained. Based on this, the “same day” prediction method is introduced, and the historical data of the first two weeks is used as training. The Gaussian regression prediction model is used to predict the basic load and electric vehicle charging demand of residential areas. Furthermore, an optimization model aimed at minimizing the load variance of the distribution network was constructed, and the water filling algorithm was used to solve the objective function. The performance of the distribution network under unordered and ordered charging conditions was compared and analyzed. The simulation results show that using the data from the first two weeks can ensure that the prediction model is based on the latest load information, while reducing the computational complexity of the model and improving the accuracy and real-time performance of the prediction. At the same time, the strategy proposed in this article reduces the load fluctuation and peak valley difference of the distribution network, achieving the “peak shaving and valley filling” of the load curve.