An Evolutionary Fuzzy System for Coordinated and Traffic Responsive Ramp Metering

This paper proposes a nonlinear approach for designing traffic responsive and coordinated ramp control using a self adapting fuzzy system. The traffic responsive metering rate is determined every minute by an adaptive fuzzy logic algorithm. The coordination between multiple on-ramps is ensured by the integration of a common input into all ramp controllers upstream of a bottleneck and a periodically update of the fuzzy system every 15 min. by a evolutionary tuning process. The objective of the genetic tuning of the fuzzy parameters is to minimize the total time spent in the system. Therefore a modified Payne traffic flow model is used. For testing the developed system a section of 25 km of the A9 Autobahn was simulated with the FREQ model. The results of the simulation of the adaptive fuzzy algorithm are very satisfying and an implementation of the ramp metering system is planned in the very near future.