Large-Scale IP Traffic Matrix Estimation Based on Backpropagation Neural Network

Abstract

Traffic matrix estimation is significantly important for operators. However, it is difficult to estimate accurately traffic matrix. This paper proposes a novel method of large-scale IP traffic matrix estimation, termed the backpropagation neural network and iterative proportional fitting procedure (BPNNIPFP). Firstly, we model the large-scale IP traffic matrix estimation using the backpropagation neural network (BPNN) that has been studied widely. By training the BPNN, we can build the model of large-scale IP traffic matrix estimation. Secondly, combined with the model and iterative proportional fitting procedure (IPFP), the good estimations of the large-scale IP traffic matrix are attained. Finally, we use the real data from the Abilene network to validate BPNNIPFP. Simulation results show that BPNNIPFP can perform the accurate estimation of large-scale IP traffic matrix, and track well its dynamics.