Internet Time-delay Prediction Based on Autoregressive and Neural Network Model

摘要：

Internet time-delay prediction plays a key role in improving dynamic performances for many real-time applications, especially for Internet-based control systems. Therefore, ideal prediction approach for Internet time-delay must be investigated emphatically. In this paper, after analyzing Internet communication features, the autoregressive model and adaptive linear neural network model are adopted to predict the uncertain Internet time-delay. The simulation results for time-delay prediction illustrate that the autoregressive model and the adaptive linear neural network provide two kind of promising ways to predict the Internet time-delay. The resulting statistics of simulation experiments also illustrates that the adaptive linear neural network has a better prediction performance than autoregressive model.

作者: Li Hongyan Wang Hong Gui Chao

作者单位: Department of Computer and Electronic Science,Hubei University of Economics, Wuhan 430205, P.R. China

会议类型: 国际会议

会议名称: 2006 International Conference on Communications,Circuits and Systems(第四届国际通信、电路与系统学术会议)

会议地点: 广西桂林

会议语种:英文

页码: 1758-1761

在线出版日期: 2006-06-25（万方平台首次上网日期，不代表论文的发表时间）