Integrated traffic corridor control using machine learning

Advancements in intelligent transportation systems and communication technology have the potential to considerably reduce delay and congestion through an array of network-wide traffic control and management strategies. Perhaps two of the most promising control tools for freeway corridors are traffic-responsive ramp metering and/or dynamic traffic diversion possibly using variable message signs (VAdS). The aim of the research approach presented in this paper is to develop a self-learning adaptive independent and integrated freeway-control for both recurring and nonrecurring congestion. The paper introduces the use of reinforcement learning, an artificial intelligence method for machine learning, to provide optimal controls using ramp metering and VMS routing independently and also as an integrated manner. Results from various simulation case studies in Toronto are very encouraging and discussed in the paper.