BP neural network is a neural network with a wide range of applications, but there are obvious defects: slow convergence and easy to fall into local minima. The genetic algorithm has the ability to search the global optimal solution with a good prediction model. In order to improve the accuracy in the prediction of BP neural network, a prediction method of genetic algorithm optimization based on BP neural network is proposed. Using genetic algorithm to optimize BP neural network weights and thresholds, and then training the BP neural network prediction model to obtain the optimal solution, and the prediction method is applied to the Buck output voltage average validated. The simulation results show that the improved method has good nonlinear fitting capability and higher the accuracy of prediction.