Genetic algorithm-based combinatorial parametric optimization for the calibration of microscopic traffic simulation models

T. Ma; B. Abdulhai; IEEE

doi:10.1109/ITSC.2001.948771

Back

Conference proceeding

Genetic algorithm-based combinatorial parametric optimization for the calibration of microscopic traffic simulation models

T. Ma, B. Abdulhai and IEEE

ITSC 2001. 2001 IEEE Intelligent Transportation Systems. Proceedings (Cat. No.01TH8585), pp.848-853

2001

DOI: https://doi.org/10.1109/ITSC.2001.948771

Abstract

Calibration

Civil engineering

Genetic algorithms

Intelligent transportation systems

Microscopy

Predictive models

Search methods

System testing

Telecommunication traffic

Traffic control

We introduce GENOSIM, genetic optimizer for traffic micro-simulation models. GENOSIM is developed as a pilot software, employing state of the art combinatorial parametric optimization to automate the tedious task of calibrating traffic microscopic simulation models. The employed global search technique, genetic algorithms, is integrated with a dynamic traffic microscopic simulation model for the City of Toronto, Canada using Paramics microsimulation suite. The output of GENOSIM is the near-optimal values of its car-following, lane changing and dynamic routing parameters. The results obtained are very encouraging.

Metrics

7 Record Views

Details

Title: Genetic algorithm-based combinatorial parametric optimization for the calibration of microscopic traffic simulation models
Creators - without role: T. Ma - Dept. of Civil Eng., Toronto Univ., Downsview, Ont., Canada
B. Abdulhai
IEEE
Publication Details: ITSC 2001. 2001 IEEE Intelligent Transportation Systems. Proceedings (Cat. No.01TH8585), pp.848-853
Publisher: IEEE
Identifiers: 9930914008331
Academic Unit: Umm Al Qura University
Language: English
Resource Type: Conference proceeding