Optimization Design Based On Traffic Volume Traffic Signal Control System

With economic development, a sharp increase in the number of private cars, urban traffic congestion issues are also increasingly prominent. The key point of intersection as urban traffic network control, efficiency tremendous impact on vehicle traffic, traffic signal control effect directly determines the performance of the entire transport network. In order to solve urban traffic congestion, although tried a variety of ways, such as widening roads, odd and even number lines, or not effectively solve the congestion problem.In this paper, after a study found that the existing traffic control systems, the existing traffic signal timing is unreasonable is the main cause of traffic congestion, and therefore this article intersection traffic signal control system to optimize the design. According to the real-time collection of traffic data using genetic algorithms traffic signal control system with dynamic optimization reasonably designed to achieve a certain degree of ease traffic congestion and reduce vehicle delay, reduce vehicle queue length, the purpose of improving the rate of vehicular traffic.Firstly, the analysis of signal control method on the basis of existing single intersection, for the characteristics of the current urban traffic dynamics, points out the shortcomings and deficiencies of traditional control methods, and the basic principles of genetic algorithms, etc. After analyzing the basic elements, For basic genetic algorithm limitations in the application of the algorithm to improve operating efficiency and to improve the quality solving. Then, based on analysis of urban single intersection traffic flow on to the traffic control signal Yinchuan Helan Road and Cross Street intersection is the source for the optimization target, first established with the shortest average delay of vehicles to phase effective green time and Saturation is a nonlinear function of the model’s constraints, the use of improved genetic algorithm optimization solution to model, optimal timing scheme at a fixed period. Simulation results show that the improved genetic algorithm intersection average delay after the vehicle model optimization has been significantly reduced. Secondly, the intersection traffic congestion, the establishment of a total of intersection of the vehicle within the control period the minimum length of the goal line to the phase of the effective green time and cycle length of the control signal traffic signal optimization model variables, the use of improved genetic algorithm the model simulation results show that the total number of vehicles queuing delays within the control cycle after optimization intersection has been significantly reduced.