Actuated traffic signal optimisation using evolutionary algorithms
Published: 2007 Juni
Buchtitel: Proceedings of the 6th European Congress and Exhibition on Intelligent Transport Systems and Services (ITS07)
Verlag: ERTICO - ITS Europe
The optimization of traffic signal systems is an important step towards successful traffic control, since delays in urban road networks depend largely on the signal system's performance. Due to their adaptivity, traffic-actuated signal controllers are widely used in traffic systems around the globe. However, their performance largely depends on the choice of appropriate control parameters. Here, we describe the application of NSGA-II, a multiobjective evolutionary algorithm, to the optimization of a traffic-actuated controller. Results show that parameters found by NSGA-II can be superior to those defined by a traffic engineer with respect to several objectives, including the resulting travel times and the necessary number of stops.