Together with the nonlinear time series analysis and the giant data samples authorized by CAIDA,the chaotic character of network delay time series indicates that its evolvement process existed chaotic identity.Then,we proposed a revised Logistic model with sine and cosine functions to describe the evolvement state of network delay.Moreover,particle swarm optimization (PSO) algorithm is adopted for the parameters estimation of the revised model,which is evaluated from the perspective of convergence,fitting accuracy and forecast accuracy.The result reviews that the structure of the optimized model is reasonable,and reflects the movement of network delay accurately.