Large-Scale IP Traffic Matrix Estimation Based on the Recurrent Multilayer Perceptron Network

Abstract

This paper proposes a novel method of large-scale IP traffic matrix estimation, based on the recurrent multiplayer perceptron (RMLP) network that is a kind of recurrent neural networks. Firstly, we model the large-scale IP traffic matrix estimation using the RMLP network that can well denote the dynamic behavior of IP network. Based on the conventional RMLP network, we present a new multi-input and multi-output RMLP network model. Then by the model, we present a novel approach to the large-scale IP traffic matrix estimation. Finally, we use the real data from the Abilene Network to validate our method. The results show that our method and model can perform well the accurate estimation of traffic matrix and track its dynamics.