With the increasing popularity of electric vehicles, the impact of EV charging behavior on the stable operation of the power grid is becoming increasingly significant, making accurate prediction of charging load highly important. This paper proposes a short-term electric vehicle charging load prediction model based on K-means clustering and WOA-BP (Whale Optimization Algorithm-Back-Propagation Network). Firstly, the model utilizes K-means clustering to group charging loads, then optimizes the parameters of the BP neural network using WOA to obtain the optimal parameter combination, and finally constructs the WOA-BP prediction model for training and prediction. Experiments are conducted based on real data, and the Monte Carlo method is employed to obtain electric vehicle charging loads. The results indicate that the proposed model effectively considers the influencing factors of charging loads and significantly improves the accuracy of electric vehicle charging load prediction.