Clustering to Enhance Network Traffic Forecasting

Conference paper
Part of the Lecture Notes in Networks and Systems book series (LNNS, volume 9)


Network traffic forecasting has become more and more vital and important in present days for monitoring the network traffic. The number of users that are connecting to network utilization is experiencing exponential growth. The accurate of modeling and forecasting network traffic is increasingly becoming significant in achieving guaranteed quality of service (QoS) in network. The enhanced QoS is maintained in the network by modeling and forecasting network. In this paper, we propose an integrated model that combines clustering with linear and nonlinear time series forecasting models, namely, Weighted Exponential Smoothing (WES), Holt-Trend Exponential Smoothing (HTES), autoregressive moving average (ARMA), Hybrid model (Wavelet with WES), and AutoRegressive Neural Network (NARNET) models to enhance forecasting of loading packets in network. The experimental results show that the integrated model can be an effective way to enhance forecasting accuracy attained with assist of derived centriods. The performance measures MSE, RMSE, and MAPE are used to evaluate the results of conventional time series models and proposed model.


Network traffic Forecasting Clustering Time series models 


  1. 1.
    Saleh AAM, Simmons JM (2011) Technology and architecture to enable the explosive growth of the internet. IEEE 49(1):126–132Google Scholar
  2. 2.
    Feng H, Shu Y (2005) Study on network traffic prediction techniques. In: Wireless communications, networking and mobile computing, 2005. IEEE, pp 1041–1044Google Scholar
  3. 3.
    Di C, Hai-Hang F, Qing-jia L, Chun-xiao C (2006) Multi-scale internet traffic prediction using wavelet neural network combined model. In: First international conference on communications and networking in China, ChinaCom 2006. IEEE, pp 1–5Google Scholar
  4. 4.
    Li J, Shen L, Tong Y (2009) Prediction of network flow based on wavelet analysis and ARIMA model. In: International conference on wireless networks and information systems, WNIS 2009. IEEE, pp 217–220Google Scholar
  5. 5.
    Rutka G (2008) Network traffic prediction using ARIMA and neural networks models. Int J Res Inf Sys 311(4):47–52Google Scholar
  6. 6.
    Wang P, Liu Y (2008) Network traffic prediction based on improved BP wavelet neural network. In: 4th international conference on wireless communications networking and mobile computing, WiCOM 2008. IEEE, pp 1–5Google Scholar
  7. 7.
    Chabaa S, Zeroual A, Antari J (2009) ANFIS method for forecasting internet traffic time series. In: Mediterranean microwave symposium (MMS). IEEE, pp 1–4Google Scholar
  8. 8.
    Kuang J, Zhai D, Wu X, Wang Y (2013) A network traffic prediction method using two-dimensional correlation and single exponential smoothing. IEEE, pp 403–406Google Scholar
  9. 9.
    Aldhyani THH, Joshi MR (2016) An integrated model for prediction of loading packets in network traffic. In: Second international conference on information and communication technology for competitive strategies. ACMGoogle Scholar
  10. 10.
    MAWI Working Group Traffic Archive, Packet traces from WIDE backbone.
  11. 11.
    Keogh E, Lin J (2005) Clustering of time-series subsequences is meaningless: implications for previous and future research. In: Knowledge and information systems. Springer, pp 154–177Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2018

Authors and Affiliations

  1. 1.School of Computer SciencesNorth Maharashtra UniversityJalgaonIndia

Personalised recommendations