Modern urban highways are under the influence of increased traffic demand and cannot fulfill the desired level of service anymore. In most of the cases there is no space available for any infrastructure building. Solutions from the domain of intelligent transport systems are used, such as ramp metering. To cope with the significant daily changes of the traffic demand, various approaches with autonomic properties like self-learning are applied for ramp metering. One of these approaches is reinforced learning. In this paper the Q-Learning algorithm is applied to learn the local ramp metering control law in a simulation environment, implemented in a VISSIM microscopic simulator. The approach proposed is tested in simulations with emphasis on the mainstream speed and travel time, using a typical on-ramp configuration.

Częstotliwość wydawania:
4 razy w roku
Dziedziny czasopisma:
Computer Sciences, Information Technology