Abstract
A typical urban traffic network is a very complicated large-scale stochastic system which consists of many interconnected signalized traffic intersections. Setting signals at intersections so that the traffic in such a network flows efficiently is a key goal in traffic management. The conventional traffic signal control algorithms assume the traffic system is deterministic; most of them use data aggregation, instead of a mathematical model, and apply off-line, heuristic control strategies which do not respond to the fluctuations of the traffic flows in the network. In this dissertation, the traffic signal control problem is formulated as a decision-making problem for a stochastic dynamical system. Based on Markovian decision theory, a new decentralized optimal control strategy with the embedded platoon dispersion model is developed to minimize the queue length and the steady state delay of traffic networks. A rolling horizon algorithm is also employed to achieve real-time adaptive traffic signal control. Statistical analysis of the computer simulation results for this approach indicates significant improvement over the traditional fully actuated control, especially under the conditions of high, but not saturated, traffic demand.
