A dynamic network loading model for traffic dynamics modeling

Hilmi Berk Celikoglu*

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

27 Citations (Scopus)


The need for a better representation of traffic dynamics and the reproduction of traffic flow motion on the network have been the main reasons to seek solutions for dynamic network loading (DNL) models. In this paper, a neural network (NN) approximator that supports the DNL model is utilized to model link flow dynamics on a sample network. The presented DNL model is constructed with a linear travel time function for link performances and an algorithm written with a set of rules considering the constraints of link dynamics, flow conservation, flow propagation, and boundary conditions. Each of the three selected NN methods, i.e., feedforward back-propagation NN, radial basis function NN, and generalized regression NN, is utilized in the integrated model structure in order to determine the most appropriate one, and hence, three DNL processes are simulated. Traffic dynamics such as inflow rates, outflow rates, and delays are selected to evaluate the performance of the proposed model.

Original languageEnglish
Pages (from-to)575-583
Number of pages9
JournalIEEE Transactions on Intelligent Transportation Systems
Issue number4
Publication statusPublished - Dec 2007


Manuscript received May 21, 2007. This work was supported in part by the Scientific and Technological Research Council of Turkey (TUBITAK) under Grant 2214. The Associate Editor for this paper was M. Brackstone. The author is with the Faculty of Civil Engineering, Department of Civil Engineering, Technical University of Istanbul, Istanbul 34469, Turkey (e-mail: celikoglu@itu.edu.tr). Digital Object Identifier 10.1109/TITS.2007.903051

FundersFunder number
Türkiye Bilimsel ve Teknolojik Araştirma Kurumu


    • Dynamic network loading (DNL)
    • Neural networks (NNs)
    • Simulation


    Dive into the research topics of 'A dynamic network loading model for traffic dynamics modeling'. Together they form a unique fingerprint.

    Cite this