Detail publikace

Evolutionary approach to calibration of cellular automaton based traffic simulation model

Originální název

Evolutionary approach to calibration of cellular automaton based traffic simulation model

Anglický název

Evolutionary approach to calibration of cellular automaton based traffic simulation model

Jazyk

en

Originální abstrakt

Microscopic traffic simulation models have become very popular in the evaluation of transportation engineering and planning practices in the past few decades. To achieve high fidelity and credibility of simulations, a model calibration and validation must be performed prior to deployment of the simulator. In this paper, we proposed an effective calibration method of the microscopic traffic simulation model. The model is based on the cellular automaton, which allows fast large-scale real-time simulation. For its calibration, we utilized a genetic algorithm which is able to optimize different parameters much better that a human expert. Furthermore, it is possible to readjust the model to given field data coming from standard surveillance technologies such as loop detectors in our case. We have shown that the precision of simulations can be increased by 20 % with respect to a manually tuned model.

Anglický abstrakt

Microscopic traffic simulation models have become very popular in the evaluation of transportation engineering and planning practices in the past few decades. To achieve high fidelity and credibility of simulations, a model calibration and validation must be performed prior to deployment of the simulator. In this paper, we proposed an effective calibration method of the microscopic traffic simulation model. The model is based on the cellular automaton, which allows fast large-scale real-time simulation. For its calibration, we utilized a genetic algorithm which is able to optimize different parameters much better that a human expert. Furthermore, it is possible to readjust the model to given field data coming from standard surveillance technologies such as loop detectors in our case. We have shown that the precision of simulations can be increased by 20 % with respect to a manually tuned model.

BibTex


@inproceedings{BUT96934,
  author="Pavol {Korček} and Lukáš {Sekanina} and Otto {Fučík}",
  title="Evolutionary approach to calibration of cellular automaton based traffic simulation model",
  annote="Microscopic traffic simulation models have become very popular in the evaluation
of transportation engineering and planning practices in the past few decades. To
achieve high fidelity and credibility of simulations, a model calibration and
validation must be performed prior to deployment of the simulator. In this paper,
we proposed an effective calibration method of the microscopic traffic simulation
model. The model is based on the cellular automaton, which allows fast
large-scale real-time simulation. For its calibration, we utilized a genetic
algorithm which is able to optimize different parameters much better that a human
expert. Furthermore, it is possible to readjust the model to given field data
coming from standard surveillance technologies such as loop detectors in our
case. We have shown that the precision of simulations can be increased by 20 %
with respect to a manually tuned model.",
  address="IEEE Intelligent Transportation Systems Society",
  booktitle="Proceedings of the 15th International IEEE Conference on Intelligent Transportation Systems",
  chapter="96934",
  doi="10.1109/ITSC.2012.6338759",
  edition="NEUVEDEN",
  howpublished="electronic, physical medium",
  institution="IEEE Intelligent Transportation Systems Society",
  year="2012",
  month="september",
  pages="122--129",
  publisher="IEEE Intelligent Transportation Systems Society",
  type="conference paper"
}