Title: Modelling of a traffic cell based on a recurrent-neural network

Authors: Marcos A. Gonzalez-Olvera, Yu Tang, Luis Alvarez-Icaza

Addresses: Universidad Autonoma de la Ciudad de Mexico – San Lorenzo Tezonco, Prolongacion San Isidro, 151, Iztapalapa 09790, Mexico City, Mexico. ' Facultad de Ingenieria, Universidad Nacional Autonoma de Mexico, Av. Universidad 3000, Coyoacan 04510, Mexico City, Mexico. ' Instituto de Ingenieria, Universidad Nacional Autonoma de Mexico, Av. Universidad 3000, Coyoacan 04510, Mexico City, Mexico

Abstract: In this paper, a continuous-time recurrent neural network for modelling a vehicle density-flow relation in a section of a highway is presented. The global objective is to make the network emulate dynamically this individual section for simulation purposes. The training algorithm is motivated from previous works in adaptive observers and uses only output measurements and the knowledge of the excitation input signal to generate the entire dynamics of the network. Training is based on the generation of estimates of an ideal network and jointly identifying its parameters. The stability and convergence of the training algorithm are established based on the Lyapunov stability theory. Model validation through numerical simulation with real data is included.

Keywords: traffic systems; traffic cells; traffic modelling; nonlinear system identification; recurrent networks; neural networks; neurofuzzy networks; vehicle density; traffic flow; model validation; numerical simulation.

DOI: 10.1504/IJMIC.2011.041781

International Journal of Modelling, Identification and Control, 2011 Vol.13 No.4, pp.259 - 268

Published online: 21 Mar 2015 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article