On the use of random neural networks for traffic matrix estimation in large-scale IP networks
Proceedings of the 6th International Wireless Communications and Mobile Computing Conference
| Hi-index | 0.00 |
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 accu-rate estimation of large-scale IP traffic matrix, and track well its dynamics.