Multi-step prediction for the network traffic based on echo state network optimized by quantum-behaved fruit fly optimization algorithm
Ying Han, Yuanwei Jing, Kun Li · 2017
The network traffic is a very important parameter to evaluate the network load and running state, and realization of the accurate prediction can be an important method to improve the network management. In this paper, a multi-step prediction method for the network traffic based on echo state network (ESN) optimized by quantum-behaved fruit fly optimization algorithm (QFOA) is proposed. First, the phase-space reconstruction technology is used to reconstruct the original network traffic data series, and then the ESN method is used to build the prediction model, and meanwhile four model parameters are optimized by the QFOA to improve the model prediction accuracy. Through the simulation experiments on the public network traffic data set, the results prove that the proposed method has better prediction effects.