Name
Abstract | ||
|---|---|---|
Network traffic prediction is not only an academic problem, but also a concern of industry and network performance department. Efficient prediction of network traffic is helpful for protocol design, traffic scheduling, detection of network attacks, etc. In this paper, we analyze real network traffic at a different time scale of three provinces, which is provided by ZTE Corporation. By means of the calculation of Hurst exponent of each traffic time series, it is proved that the network traffic data are self-similar, which indicates that we can predict network traffic utilizing nonlinear time series models. In this paper, the Echo State Network is applied. Meanwhile, rigid regression method is applied to avoid the weak-conditioned problem and the gird search algorithm is used to optimize the reservoir parameters and coefficients. The result shows that our approach can predict network traffic efficiently, which is also a verification of the self-similarity analysis. |
Year | DOI | Venue |
|---|---|---|
2019 | 10.1109/BigDataService.2019.00045 | 2019 IEEE Fifth International Conference on Big Data Computing Service and Applications (BigDataService) |
Keywords | Field | DocType |
network traffic,self-similarity,echo state network | Data mining,Nonlinear system,Search algorithm,Regression,Computer science,Scheduling (computing),Hurst exponent,Echo state network,Self-similarity,Network performance | Conference |
ISBN | Citations | PageRank |
978-1-7281-0060-9 | 0 | 0.34 |
References | Authors | |
0 | 4 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Yan Xu | 1 | 0 | 0.34 |
| Summera Shamrooz Aslam | 2 | 0 | 0.34 |
| Li Qian-Mu | 3 | 33 | 14.78 |
| Jun Hou | 4 | 4 | 4.14 |