A neural network-based simultaneous perturbation stochastic approximation approach to traffic signal timing control

Research output: Contribution to journalArticlepeer-review

Abstract

A sudden traffic surge immediately after special events (e.g., conventions, sporting events, concerts, etc.) can create substantial traffic congestion in the area where the events are held. It is desired to implement a short-term traffic signal timing adjustment for the high volume traffic movements associated with special events so that progression is as efficient as possible. This paper presents a study of special events traffic signal timing control for the City of Duluth Entertainment and Convention Center (DECC). Although it presents a case study, the results can be easily applied to large-scale events held in other cities and urban areas. A practical method for signal timing control that eliminates the need of using traffic model is proposed. Our approach is based on neural networks (NNs) with the weight estimation via the Simultaneous Perturbation Stochastic Approximation (SPSA) method. The NN weights are determined by use of the SPSA algorithm that minimizes a tolerance index at the six -intersection network following DECC special events. The traffic timing plan is developed and the performance evaluations using the existing signal timing and the one generated by the SPSA algorithm are also compared. Our results show the advantage and potential of using the NN-based SPSA optimization method to traffic signal timing control study.

Original languageEnglish (US)
Pages (from-to)197-205
Number of pages9
JournalWSEAS Transactions on Systems
Volume4
Issue number3
StatePublished - Mar 1 2005
Externally publishedYes

Keywords

  • Measure of effectiveness
  • Neural networks
  • Optimization
  • Simultaneous perturbation stochastic approximation
  • Traffic signal timing control

Fingerprint Dive into the research topics of 'A neural network-based simultaneous perturbation stochastic approximation approach to traffic signal timing control'. Together they form a unique fingerprint.

Cite this