Citation

Armas R, Aguirre H, Daolio F, Tanaka K. PLoS One 2017; 12(12): e0188757.

Affiliation

Faculty of Engineering, Shinshu University. 4-17-1 Wakasato, Nagano 380-8553, Japan.

Copyright

(Copyright © 2017, Public Library of Science)

DOI

10.1371/journal.pone.0188757

PMID

29236733

Abstract

This work applies evolutionary computation and machine learning methods to study the transportation system of Quito from a design optimization perspective. It couples an evolutionary algorithm with a microscopic transport simulator and uses the outcome of the optimization process to deepen our understanding of the problem and gain knowledge about the system. The work focuses on the optimization of a large number of traffic lights deployed on a wide area of the city and studies their impact on travel time, emissions and fuel consumption. An evolutionary algorithm with specialized mutation operators is proposed to search effectively in large decision spaces, evolving small populations for a short number of generations. The effects of the operators combined with a varying mutation schedule are studied, and an analysis of the parameters of the algorithm is also included. In addition, hierarchical clustering is performed on the best solutions found in several runs of the algorithm. An analysis of signal clusters and their geolocation, estimation of fuel consumption, spatial analysis of emissions, and an analysis of signal coordination provide an overall picture of the systemic effects of the optimization process.

Language: en