ETRI Journal

Electronics and Telecommunications Research Institute (한국전자통신연구원)
권호 표지
DOI QR코드

DOI QR Code

Network traffic prediction model based on linear and nonlinear model combination

  • Lian Lian (College of Information Engineering, Shenyang University of Chemical Technology)
  • Received : 2023.03.31
  • Accepted : 2023.06.05
  • Published : 2024.06.20
Download PDF
⟨ Previous Next ⟩

Abstract

We propose a network traffic prediction model based on linear and nonlinear model combination. Network traffic is modeled by an autoregressive moving average model, and the error between the measured and predicted network traffic values is obtained. Then, an echo state network is used to fit the prediction error with nonlinear components. In addition, an improved slime mold algorithm is proposed for reservoir parameter optimization of the echo state network, further improving the regression performance. The predictions of the linear (autoregressive moving average) and nonlinear (echo state network) models are added to obtain the final prediction. Compared with other prediction models, test results on two network traffic datasets from mobile and fixed networks show that the proposed prediction model has a smaller error and difference measures. In addition, the coefficient of determination and index of agreement is close to 1, indicating a better data fitting performance. Although the proposed prediction model has a slight increase in time complexity for training and prediction compared with some models, it shows practical applicability.

Keywords

Acknowledgement

The author would like to thank the editor and all anonymous reviewers for their helpful feedback.

References

  1. S. Izadi, M. Ahmadi, and A. Rajabzadeh, Network traffic classification using deep learning networks and Bayesian data fusion, J. Netw. Syst. Manag. 30 (2022), no. 2, 25.
  2. Z. D. Tian and F. H. Li, Network traffic prediction method based on autoregressive integrated moving average and adaptive Volterra filter, Int. J. Commun. Syst. 34 (2021), no. 12, e4891.
  3. Z. D. Tian, Chaotic characteristic analysis of network traffic time series at different time scales, Chaos Solitons Fractals 130 (2020), 109412.
  4. K. Zhou, W. Wang, L. Huang, and B. Liu, Comparative study on the time series forecasting of web traffic based on statistical model and generative adversarial model, Knowl. Based Syst. 213 (2021), 106467.
  5. Q. T. Tran, L. Hao, and Q. K. Trinh, A comprehensive research on exponential smoothing methods in modeling and forecasting cellular traffic, Concurrency Comput. Pract. Exper. 32 (2020), no. 23, e5602.
  6. U. Premaratne and U. S. Premarathne, A sum of Bernoulli sources approximation for packet switched network traffic in backbone links, IEEE Commun. Lett. 24 (2020), no. 1, 141-145.
  7. A. Domanski, J. Doma nska, K. Filus, J. Szygu la, and T. Czachorski, Self-similar Markovian sources, Appl. Sci. Basel 10 (2020), no. 11, 3727.
  8. Y. Xie, J. Hu, Y. Xiang, S. Yu, S. Tang, and Y. Wang, Modeling oscillation behavior of network traffic by nested hidden Markov model with variable state-duration, IEEE Trans. Parallel Distrib. Syst. 24 (2013), no. 9, 1807-1817.
  9. M. Laner, P. Svoboda, and M. Rupp, Parsimonious fitting of long-range dependent network traffic using ARMA models, IEEE Commun. Lett. 17 (2013), no. 12, 2368-2371.
  10. Q. Yu, L. Jibin, and L. R. Jiang, An improved ARIMA-based traffic anomaly detection algorithm for wireless sensor networks, Int. J. Distrib. Sens. Netw. 12 (2016), no. 1, 9653230.
  11. S. Dong, Multi class SVM algorithm with active learning for network traffic classification, Expert Syst. Appl. 176 (2021), 114885.
  12. J. X. Liu and Z. H. Jia, Telecommunication traffic prediction based on improved LSSVM, Int. J. Pattern Recognit. Artif. Intell. 32 (2018), no. 3, 1850007.
  13. V. K. Chauhan, K. Dahiya, and A. Sharma, Problem formulations and solvers in linear SVM: a review, Artif. Intell. Rev. 52 (2019), no. 2, 803-855.
  14. J. Zhou, H. Wang, F. Xiao, X. Yan, and L. Sun, Network traffic prediction method based on echo state network with adaptive reservoir, Softw. Pract. Exper. 51 (2021), 2238-2251.
  15. X. L. Zheng, W. Lai, H. Chen, S. Fang, and Z. Li, A study of cellular traffic data prediction by kernel ELM with parameter optimization, Appl. Sci. Basel 10 (2020), no. 10, 3517.
  16. Y. Hou, L. Zhao, and H. W. Lu, Fuzzy neural network optimization and network traffic forecasting based on improved differential evolution, Internat. J. Engrg. Sci. 81 (2018), 425-432.
  17. D. F. Wei, Network traffic prediction based on RBF neural network optimized by improved gravitation search algorithm, Neural Comput. Appl. 28 (2017), no. 8, 2303-2312.
  18. K. T. Selvi and R. Thamilselvan, An intelligent traffic prediction framework for 5G network using SDN and fusion learning, Peer-to-Peer Netw. Appl. 10 (2022), 7003-7015.
  19. M. Emec and M. H. Ozcanhan, A hybrid deep learning approach for intrusion detection in IoT networks, Adv. Electr. Comput. Eng. 22 (2022), no. 1, 3-12.
  20. Y. Han, Y. W. Jing, and G. M. Dimirovski, An improved fruit fly algorithm-unscented Kalman filter-echo state network method for time series prediction of the network traffic data with noises, Trans. Inst. Meas. Control. 42 (2020), no. 7, 1281-1293.
  21. X. C. Tan, H. Ma, S. Yu, and J. Hu, Recognizing the content types of network traffic based on a hybrid DNN-HMM model, J. Netw. Comput. Appl. 142 (2019), 51-62.
  22. M. L. Yuan, Jitter buffer control algorithm and simulation based on network traffic prediction, Int. J. Wirel. Inf. Netw. 26 (2019), no. 3, 133-142.
  23. Z. D. Tian, Network traffic prediction method based on wavelet transform and multiple models fusion, Int. J. Commun. Syst. 33 (2020), no. 11, e4415.
  24. L. Lian and Z. D. Tian, Network traffic prediction model based on ensemble empirical mode decomposition and multiple models, Int. J. Commun. Syst. 34 (2021), no. 17, e4966.
  25. Y. Han, Y. Jing, K. Li, and G. M. Dimirovski, Network traffic prediction using variational mode decomposition and multireservoirs echo state network, IEEE Access 7 (2019), 138364-138377.
  26. L. L. Ren, A. A. Heidari, Z. Cai, Q. Shao, G. Liang, H.-L. Chen, and Z. Pan, Gaussian kernel probability-driven slime mould algorithm with new movement mechanism for multi-level image segmentation, Measurement 192 (2022), 110884.