In order to overcome the shortcomings of wavelet neural network and improve prediction precision of network traffic, a novel network traffic prediction model is proposed based on the wavelet neural network and genetic algorithm in this paper. Firstly, the time delay and embedding dimension of network traffic are calculated to construct the learning samples of wavelet neural network. Then training samples are input to wavelet neural network to learn in which improved genetic algorithm is used to optimize the parameters of wavelet neural network. Finally, the performance of model is tested by simulation experiment using network traffic data. The results show that the proposed model has reduced the prediction error and the number of training has reduced sharply compared with other model, so it has great practical application value.