An Evolutionary Based Approach for the Traffic Lights Optimization Problem

Ivan Davydov, Daniil Tolstykh

Research output: Chapter in Book/Report/Conference proceedingConference contributionResearchpeer-review

1 Citation (Scopus)

Abstract

We consider the traffic lights optimization problem which arises in city management due to continuously growing traffic. Given a road network and predictions (or statistical data) about the traffic flows through the arcs of this network the problem is to define the offsets and phase length for each traffic light in order to improve the overall quality of the service. The latter can be defined through a number of criteria, such as average speed, average trip duration, total waiting time etc. For this problem, we present an evolutionary based heuristic approach. We use a simulation model on the basis of the SUMO modeling system to evaluate the quality of obtained solutions. The results of numerical experiments on real data confirm the efficiency of the proposed approach.

Original languageEnglish
Title of host publicationMathematical Optimization Theory and Operations Research - 18th International Conference, MOTOR 2019, Revised Selected Papers
EditorsIgor Bykadorov, Vitaly Strusevich, Tatiana Tchemisova
PublisherSpringer International Publishing AG
Pages19-29
Number of pages11
ISBN (Print)9783030333935
DOIs
Publication statusPublished - 1 Jan 2019
Event18th International Conference on Mathematical Optimization Theory and Operations Research, MOTOR 2019 - Ekaterinburg, Russian Federation
Duration: 8 Jul 201912 Jul 2019

Publication series

NameCommunications in Computer and Information Science
Volume1090 CCIS
ISSN (Print)1865-0929
ISSN (Electronic)1865-0937

Conference

Conference18th International Conference on Mathematical Optimization Theory and Operations Research, MOTOR 2019
CountryRussian Federation
CityEkaterinburg
Period08.07.201912.07.2019

Keywords

  • Evolutionary algorithm
  • Simulation modeling
  • SUMO
  • Traffics lights sheduling

Fingerprint

Dive into the research topics of 'An Evolutionary Based Approach for the Traffic Lights Optimization Problem'. Together they form a unique fingerprint.

Cite this