Computational & Technology Resources
an online resource for computational,
engineering & technology publications
PROCEEDINGS OF THE FIFTH INTERNATIONAL CONFERENCE ON PARALLEL, DISTRIBUTED, GRID AND CLOUD COMPUTING FOR ENGINEERING
Calibrating a Traffic Flow Model with Parallel Differential Evolution
G.A. Strofylas, K.N. Porfyri, I.K. Nikolos, A.I. Delis and M. Papageorgiou
School of Production Engineering and Management, Technical University of Crete, Chania, Crete, Greece
G.A. Strofylas, K.N. Porfyri, I.K. Nikolos, A.I. Delis, M. Papageorgiou, "Calibrating a Traffic Flow Model with Parallel Differential Evolution", in , (Editors), "Proceedings of the Fifth International Conference on Parallel, Distributed, Grid and Cloud Computing for Engineering", Civil-Comp Press, Stirlingshire, UK, Paper 26, 2017. doi:10.4203/ccp.111.26
Keywords: parallel differential evolution, surrogate models, artificial neural networks, macroscopic traffic flow modeling.
Given the importance of the credibility and validity required in macroscopic traffic flow models while performing real-word simulations, the necessity of employing an efficient, computationally fast and reliable constrained optimization scheme for model calibration appears to be mandatory to ensure that the traffic flow characteristics are accurately represented by such models. To this end, a parallel, metamodel-assisted Differential Evolution (DE) algorithm is employed for the calibration of the secondorder macroscopic gas-kinetic traffic flow (GKT) model using real traffic data from Attiki Odos freeway in Athens, Greece. The parallelization of the DE algorithm is performed using Message Passing Interface (MPI), while artificial neural networks (ANNs) are used as surrogate models. Numerical simulations are performed, which demonstrate that the DE algorithm can be effectively used for the search of the globally optimal model parameters in the GKT model; in fact the method appears to be promising for the calibration of other similar traffic models as well.
purchase the full-text of this paper (price £22)