Traffic along a freeway varies not only with time but also with space. It is thus essential to model dynamic traffic patterns on the freeway in order to derive appropriate metering control strategies. Existing methods cannot fulfill this task effectively. Due to their learning capability, artificial neural network models are developed to simulate typical time series traffic data and then expanded to capture the inherent time-space interrelations. An augmented-type network is proposed that includes several basic modules intelligently affiliated according to traffic characteristics on the freeway. The inputs to the neural network models are the traffic states in each time period on the freeway segments, while the outputs correspond to the desired metering rate at each entrance ramp. The simulation outcomes indicate very encouraging achievements when the proposed neural network model is employed to govern the freeway traffic operations. Also discussed are feasible directions for further improvements.
Analysis of artificial neural network models for freeway ramp metering control
Artifical Intelligence in Engineering ; 15 , 3 ; 241-252
2001
12 Seiten, 23 Quellen
Aufsatz (Zeitschrift)
Englisch
Freeway ramp metering using artificial neural networks
Online Contents | 1997
|A Local Neural Network Controller for Freeway Ramp Metering
British Library Conference Proceedings | 1995
|Freeway Ramp Metering: An Overview
British Library Online Contents | 2002
|Freeway ramp metering: an overview
IEEE | 2000
|Freeway Optimization Utilizing Ramp Metering
British Library Conference Proceedings | 1994
|