Construction a Neural-Net Model of Network Traffic Using the Topologic Analysis of Its Time Series Complexity

Three different analysis methods was put forward to carried out aircraft aluminum alloy structure corrosion damage forecasting,and comparison analysis of different method which included basic forecasting caculation principle and forecasting accuracy and forecasting extensionality also was discussed.The forecasting calculation result shows that the prediction accuracy of neural net and time series method is higher than the data fitting method,and the prediction extensionality of time series method is the best among the three method which discussed.

Download Full-text

Construction of C-ON/OFF network traffic model based on time series

Journal of Intelligent & Fuzzy Systems ◽

10.3233/jifs-169641 ◽

2018 ◽

Vol 35 (3) ◽

pp. 2867-2877

Author(s):

Yi Liu ◽

Tian Song ◽

Le-Jian Liao

Keyword(s):

Time Series ◽

Network Traffic ◽

Traffic Model ◽

Model Based ◽

Network Traffic Model

Download Full-text

Performance of modeling time series using nonlinear autoregressive with eXogenous input (NARX) in the network traffic forecasting

2015 International Conference on Science in Information Technology (ICSITech) ◽

10.1109/icsitech.2015.7407797 ◽

2015 ◽

Cited By ~ 1

Author(s):

Haviluddin ◽

Rayner Alfred

Keyword(s):

Time Series ◽

Network Traffic ◽

Traffic Forecasting ◽

Nonlinear Autoregressive

Download Full-text

A Traffic Prediction Method Based on the Hybrid Model of CLWT

Applied Mechanics and Materials ◽

10.4028/www.scientific.net/amm.713-715.1564 ◽

2015 ◽

Vol 713-715 ◽

pp. 1564-1569

Author(s):

Jin Long Fei ◽

Wei Lin ◽

Tao Han ◽

Yue Fei Zhu

Keyword(s):

Time Series ◽

Hybrid Model ◽

Network Traffic ◽

Prediction Models ◽

Prediction Method ◽

Support Vector ◽

Prediction Methods ◽

Recurrent Nerve ◽

Nerve Network ◽

Traffic Time Series

Current prediction models for network traffic cannot accurately depict the multi-properties of the Internet traffic. This paper proposes a wavelet-based hybrid model prediction method for network traffic called CLWT model and proposes a prediction method for traffic based on this model. The traffic time series can be rapidly decomposed respectively into approximate time series and detail time series with LF and HF response. The approximate time series predicts by making use of Least Squares Support Vector Machine and proceeds error calibration by using Generalized Recurrent Nerve Network. The detail time series predict it by making use of self-adaption chaotic prediction methods after the medium-soft threshold noise reduction. Finally the prediction value of time series is got by making use of promoting wavelet reconstitution. The effectiveness for the prediction methods mentioned in the paper has been validated by simulation experiment. High prediction accuracy is obtained compared with the existing methods.

Download Full-text