Backbone Network Traffic Prediction Based on Modified EEMD and Quantum Neural Network

Abstract

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–Ribiere–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.