Traffic congestion causes unnecessary delay, pollution and increased fuel consumption. In this thesis this problem is addressed by proposing new algorithmic techniques to reduce traffic congestion and is contributed to the development of a new Intelligent Transportation System. A method is presented to determine speed limits, in which a traffic flow model is combined with reinforcement learning techniques. A traffic flow optimization problem is formulated as a Markov Decision Process, and subsequently solved using Q-learning enhanced with value function approximation. This results in a single-agent and multi-agent approach to assign speed limits to highway sections. A difference between this work and existing approaches is that also traffic predictions are taken into account. The performance of this method is evaluated in macroscopic simulations, in which it is shown that it is able to significantly reduce congestion under high traffic demands. A case study has been performed to evaluate the effectiveness of our method in microscopic simulations. The case study serves as a proof of concept and shows that the presented method performs well on a real scenario. (Author/publisher)
Samenvatting