With the popularization of environmental protection ideas, people are increasingly valuing low-carbon lifestyles and the economy. Electric vehicles play a crucial role in this transformation to reduce carbon emissions. However, integrating electric vehicles into the power grid poses challenges, especially the possibility of destructive load peaks, which may endanger the stability and safety of the power grid. Accurately predicting the load of electric vehicles and managing grid scheduling are crucial for solving this problem. The current solutions are mainly divided into two categories: statistics-based methods and machine learning-based methods. Statistical methods require a large amount of long-term data modeling, making data collection a significant challenge. Similarly, machine learning-based methods have good long-term prediction performance on high-quality data, but they do not perform well in terms of short-term prediction accuracy. To overcome these obstacles, a comprehensive electric vehicle charging load prediction framework is proposed, which utilizes an innovative variational autoencoder to generate adversarial networks (VAE-GAN) for data processing, Principal Component Analysis (PCA) for feature extraction, and an improved CNN-GRU model for prediction. The experimental results show that the accuracy of short-term power load prediction is significantly improved, which verifies the effectiveness of the framework in processing small sample load data and provides advanced tools for intelligent management of electric vehicle charging stations.