OACTS: Mathematical Model for Optimizing the Active Control of Traffic Signals Parameters

EasyChair Preprint 10304

Abstract

The number of vehicles circulating in Brazilian urban centers has increased significantly, but public mobility policies have not been sufficient to follow this growth. The consequence is the increase of traffic congestion. Faced with this scenario, there are several studies on Computational Intelligence in traffic control. In this context, this paper presents a new mathematical model: OACTS - Optimization of the Active Control of Traffic Signals. This model uses Genetic Algorithm to optimize traffic signal parameters: green time, cycle time, phase sequence and offset. For this purpose, the model proposes a new delay time function to evaluate the solutions of the algorithm. A case study is developed in which real vehicle demand data is loaded into the AIMSUN simulator. This simulator is previously calibrated to better represent real conditions. The model receives the demand from AIMSUN and, based on the application of GA, defines the value of traffic parameters in real time to meet the demand to reduce the delay of vehicles. The experiments were statistically analyzed and the results show that OACTS found better solutions to the problem compared to other models that optimize a smaller set of parameters and to the traffic plan currently used in the region.

Keyphrases: Active Traffic Management, Intelligent Transport Systems, Traffic Signal Programming

@booklet{EasyChair:10304,
  author    = {Samara Leal and Paulo Almeida},
  title     = {OACTS: Mathematical Model for Optimizing the Active Control of Traffic Signals Parameters},
  howpublished = {EasyChair Preprint 10304},
  year      = {EasyChair, 2023}}