A Simulation Experimental Study of Traffic Signal Control by Using Genetic Algorithm.

Abstract

In urban street networks, traffic flow is seriously affected by traffic signals. A traffic signal is controlled by using three parameters, cycle, split and offset and these parameters should be determined based on traffic conditions. This paper discusses on the optimal signal control in small street networks. First, we apply genetic algorithm to the optimization of signal control parameters. In this approach, we use the microscopic traffic simulation for calculating fitness value. Secondly, we analyze the optimal signal control in small networks as comparing with the results of conventional approaches and prove effectiveness of our proposed approach. Further, we propose the practical method of setting signal control parameters based on traffic conditions. 784T. IEE Japan,No. 6, '95