The accurate prediction of network traffic has great value to the formulation of intelligent scheduling strategy and the efficient optimization of network resources.A hybrid deep learning model TAN,which combines temporal convolutional networks and attention mechanisms,is proposed to improve the accuracy of network traffic prediction.The model uses fully integrated empirical mode decomposition technology to finely decompose original network traffic data,separate and process traffic changes of different scales,capture short-term local features of network traffic through time convolution,use GRU module to deeply explore the dependency relationship between long-term data,and introduce attention mechanism to enhance the model's ability to focus on key information,so as to improve the accuracy and robustness of the prediction.
维普
万方数据