Traffic Enforcement Mechanism in ATM using Neural Network

Abstract

In our paper, a novel policing mechanism using neural networks (NNs) is proposed. The mechanism is based upon an accurate estimation of the probability density function (pdf) of the traffic via its count process and implemention using NNs. The pdf based policing requires complex calculations in real time, at very high speeds, which is not feasible via conventional mathematical approaches. The proposed traffic enforcement model is elaborate and more accurate method, which exploits the effectiveness of neural network in learning and predicting non-linear complex functions at high speed. It is a suitable tool to be employed for variable bit rate policing of real time traffic in ATM networks.

Additional information

Notes on contributors

K Jayanthi

K Jayanthi received BE degree from University of Madras in 1997 and MTech degree in Electronics and Communication Engineering from Pondicherry Engineering College Pondicherry in 1999. She has five years of teaching experience. She is currently working as lecturer in the Department of Electronics and Communication Engineering, Pondicherry Engineering College, Pondicherry. She has also presented papers in more than 5 National and International conferences. Her areas of interests include Wireless Communications and Multimedia Networks.

P Dananjayan

P Dananjayan received ?Sc degree in physics from University of Madras, in 1979, ?Tech and MTech degrees in Electronics Engineering from Madras Institute of Technology in 1982 and 1984 respectively and PhD degree from Anna University, Chennai in 1988. He has 20 years of experience in teaching/research. He is currently working as Professor and Head in the Department of Electronics and Instrumentation Engineering, Pondicherry Engineering College, Pondicherry. He has ten publications in National and International Journals. He has presented papers in more than 50 National and International conferences. He has also authored two books titled Electromagnetic Engineering and Electromagnetic waves and waveguides. He is currently guiding five PhD students. His areas of interests include ATM networks. Wireless communication and Spread spectrum techniques.