Recurrent Neural Network Inference of Internal Delays in Nonstationary Data Network

By applying tomography theory which is highly developed in fieldssuchas medical computerized tomography and seismic tomography to communication network, network tomography has become one of the focused new technologies, which can infer the internal performance of the network by external end-to-end measurement. In this paper, we propose a novel Inference algorithm based on the recurrent multilayer perceptron (RMLP) network capable of tracking nonstationary network behavior and estimating time-varying, internal delay characteristics. Simulation experiments demonstrate the performance of the RMLP network.

[1]  Paul J. Werbos,et al.  Backpropagation Through Time: What It Does and How to Do It , 1990, Proc. IEEE.

[2]  Parasuram Padmanabhan Harihara.  Real-time implementation of a neural networks-based motor speed filter using a digital signal processor , 2002 .

[3]  Robert D. Nowak,et al.  Network delay tomography , 2003, IEEE Trans. Signal Process..

[4]  Bin Yu,et al.  Maximum pseudo likelihood estimation in network tomography , 2003, IEEE Trans. Signal Process..

[5]  Robert D. Nowak,et al.  Sequential Monte Carlo inference of internal delays in nonstationary data networks , 2002, IEEE Trans. Signal Process..

[6]  G. V. Puskorius,et al.  Training controllers for robustness: multi-stream DEKF , 1994, Proceedings of 1994 IEEE International Conference on Neural Networks (ICNN'94).

[7]  Shuhui Li,et al.  Wind power prediction using recurrent multilayer perceptron neural networks , 2003, 2003 IEEE Power Engineering Society General Meeting (IEEE Cat. No.03CH37491).