Arrival Rate Identification for a Class of Traffic Signal Control Problem

Setting signals at traffic intersections to reduce congestion is one of the most challenging problems in traffic management. To find the optimal control strategy, specific information of the traffic flows passing through intersections, such as vehicle arrival rates (number of vehicles per hour), must be provided in advance. In most control approaches, this parameter is assumed to be a known constant; however, for an on-line adaptive control in real-time, when this information is not available, or when it fluctuates around its nominal value, parameter estimationlidentification becomes crucial. It has been shown that the Markovian decision control theory can be successfully applied to solve traffic signal control problems, when both the state transition probabilities and the one-step reward function are known. For a class of controlled Markov processes in which each state transition probability is a function of an unknown parameter, an on-line estimation algorithm needs to be developed to identify the unknown parameter fxst; then an optimal adaptive control law can be generated to maximize the long-term total expected reward based on this estimate. In this case, the choice of the feedback control law “interacts” with the parameter identification, which is also known as the “dual” aspect for adaptive control. In this paper, an on-line parameter identification algorithm is investigated for adaptive Markovian decision control at an isolated traffic intersection with unknown vehicle viva1 rates. Section 1 gives a brief introduction to Markovian control processes and a maximum likelihood estimation algorithm. Section 2 discusses the traffic dynamic equations and the adaptive Markovian decision control model for an isolated traffic intersection. The proposed algorithm is then tested by computer simulation and the result is shown in section 3.