The traditional network traffic prediction model has the disadvantages of weak generalization ability and low prediction accuracy. In order to solve this problem, this paper developed a network traffic prediction model based on the LSTM recurrent neural network. Firstly, it improved resampling process of PF with distance comparison and optimized combination strategy. Then, it built a PF-LSTM network model to accurately predict the network traffic. Model training with improved PF algorithm improved its training rate and overcame the shortcomings of convergence in the traditional LSTM network. Finally, it predicted network traffic through proposed model. The experimental results show that the model has better prediction accuracy and convergence efficiency compared with the traditional LSTM model, which can describe the trend of changes better in network traffic.

[2019-12-05] Printed Article /doc/2018.06.0394/v2