Adaptive traffic signal control with iterative genetic fuzzy logic controller (GFLC)

Yu-Chiun Chiou*, Lawrence W. Lan

*Corresponding author for this work

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

8 Scopus citations

Abstract

An iterative evolution algorithm for selecting the logic rules and tuning the membership functions for a signalized intersection with genetic fuzzy logic controller (GFLC) is proposed. The GFLC model employs traffic flow and queue length as state variables, extension of green time as control variable and total vehicle delays estimated by fluid approximation method as performance measurement criterion. Validations from an experimental example and a field case show that our GFLC model can perform almost the same as the optimal multiple timing plan and far superior to the optimal single, Webster, and current timing plans. As traffic flows randomly vary by 10%, 30% and 50%, the GFLC model can even perform better than the optimal multiple timing plan. The results suggest that our GFLC model is effective, robust and applicable for adaptive traffic signal control.

Original languageEnglish
Title of host publicationConference Proceedings - 2004 IEEE International Conference on Networking, Sensing and Control
Pages287-292
Number of pages6
DOIs
StatePublished - 28 Jun 2004
EventConference Proceeding - 2004 IEEE International Conference on Networking, Sensing and Control - Taipei, Taiwan
Duration: 21 Mar 200423 Mar 2004

Publication series

NameConference Proceeding - IEEE International Conference on Networking, Sensing and Control
Volume1

Conference

ConferenceConference Proceeding - 2004 IEEE International Conference on Networking, Sensing and Control
CountryTaiwan
CityTaipei
Period21/03/0423/03/04

Keywords

  • Adaptive traffic signal control
  • Genetic fuzzy logic controller
  • Iterative evolution algorithm

Fingerprint Dive into the research topics of 'Adaptive traffic signal control with iterative genetic fuzzy logic controller (GFLC)'. Together they form a unique fingerprint.

Cite this