Backbone Network Traffic Prediction Based on Modified EEMD and Quantum Neural Network
- 127 Downloads
Aiming at the long-range dependence and short-range dependence characteristics of backbone network traffic, a traffic forecasting model based on Modified Ensemble Empirical Mode Decomposition (MEEMD) and Quantum Neural Network (QNN) is presented. Firstly, the MEEMD method is employed to decompose the traffic data sequence into intrinsic mode function (IMF) component. Then, the Quantum Neural Network is adopted to forecast the IMF components. Ultimately, the final prediction value is obtained via synthe-tizing the prediction results of all components. The QNN is composed of universal quantum gates and quantum weighted, and its learning algorithm employs the Modified Polak–Ribière–Polyak Conjugate Gradient method. The forecast results on real network traffic show that the proposed algorithm has a lower computational complexity and higher prediction accuracy than that of EMD and Auto Regressive Moving Average, EMD and Support Vector Machines, EEMD and Artificial Neural Networks method.
KeywordsBackbone network traffic Modified ensemble empirical mode decomposition Quantum neural network PRP conjugate gradient Traffic prediction
The authors would like to thank the anonymous reviewers for their valuable suggestions that improved this work.
This study was funded by National Natural Science Foundation of China (61672471), National Natural Science Foundation of China (61502436) and 2016 annual Henan technological innovation (164100510019).
Compliance with Ethical Standards
Conflict of interest
The authors declare that they have no conflict of interest.
- 1.Park, J., Raza, S. M., Thorat, P., Kim, D. S., & Choo, H. (2015). Network traffic prediction model based on training data. In Computational Science and Its Applications–ICCSA 2015, (pp. 117–127). Berlin: Springer.Google Scholar
- 2.Smirnov, A. A., & Danilenko, Dmitriy. (2014). Experimental studies of the statistical properties of network traffic based on the BDS-statistics. International Journal of Computational Engineering Research (IJCER), 4(5), 41–51.Google Scholar
- 3.Gao, B., Zhang, Q. Y., Liang, Y. S., Liu, N. N., Huang, C. B., & Zhang, N. T. (2011). Predicting self-similar networking traffic based on EMD and ARMA. Journal of China Institute of Communications, 32(4), 47–56.Google Scholar
- 4.Zhihui, Z., Yunlian, S., & Yu, J. (2007). Short term load forecasting based on EMD and SVM. High Voltage Engineering, 33(5), 118–122.Google Scholar
- 6.Jiang, S. B., Bai, C. F., & Du, C. F. (2014). Traffic forecast based on empirical mode decomposition and RBF neural network. Advanced Materials Research, 846, 1270–1273.Google Scholar
- 9.Kwon, S., & Cho, S. (2014). Analysis of acoustic signal based on modified ensemble empirical mode decomposition. In Transactions on Engineering Technologies, (vol. 25, no. 2, pp. 377–386) Dordrecht: Springer.Google Scholar
- 10.Nayak, S., & Singh, J. P. (2011). An intriduction to quantum neural computing. Journal of Gloabal Research in Computer Science, 2(8), 50–55.Google Scholar
- 13.Xu, W., Wang, R., Gu, X., & Sun, Y. (2013). Assessment of texaco syngas components using extreme learning machine based quantum neural network. In Intelligent Computing for Sustainable Energy and Environment, (vol. 355, pp. 221–229). Berlin: Springer.Google Scholar
- 20.Zoutendijk, G. (1970). Nonlinear programming computational methods. In J. Abadie (Ed.), Integer and nonlinear programming (pp. 37–86). Amsterdam: North-Holland.Google Scholar