Computational Urban Network Control: Using Schedule-Driven Traffic Control to Mitigate Network Congestion

Recent work in decentralized, schedule-driven traffic control
has demonstrated the ability to improve the efficiency of traffic flow in complex urban road networks. In this approach, a scheduling agent is associated with each intersection. Each agent senses the traffic approaching its intersection and in real-time constructs a schedule that minimizes the cumulative wait time of vehicles approaching the intersection over the current look-ahead horizon. In order to achieve network-level coordination in a scalable manner, scheduling agents communicate only with their direct neighbors.
Each time an agent generates a new intersection schedule it communicates its expected out flows to its downstream neighbors as a prediction of future demand and these out
flows are appended to the downstream agent's locally perceived demand. In this thesis, we study how to upgrade the network-level coordination of schedule-driven traffic control to tackle increasingly serious traffic congestion from three aspects: stability, optimality and learnability. For stability, a hybrid approach that incorporates
the stability of queuing theory into a schedule-driven control
framework is proposed. For optimality, the basic coordination protocol is extended to additionally incorporate the complementary flow of information re
effective of an intersection's current congestion level to its upstream neighbors. We propose an asynchronous
decentralized algorithm in order to approach networkwide
optimality. In addition, we show that integrating connected
and autonomous vehicles with the intersection control could provide benefits for further improving performance. To present its learnability, we study a parameter learning problem to configure maximum green time by a fully decentralized reinforcement learning algorithm and a timing prediction problem utilizing the cluster representation for scheduling approaching vehicles. The goal of this thesis is to demonstrate the capability of schedule driven traffic control to mitigate urban network congestion. To
achieve this goal, we leverage the techniques originated from online planning, distributed optimization and reinforcement learning as well as incorporate the new technologies including connected and autonomous vehicles into the schedule-driven framework.