Urban traffic control optimization method based on adaptive dynamic programming

The invention belongs to the technical field of traffic control, and discloses an urban traffic control optimization method based on adaptive dynamic programming. According to the method, the optimized boundary control law can be calculated without knowing parameters of a macroscopic fundamental diagram traffic model, and the continuity and stability of the input control quantity can be ensured. Establishing an urban macroscopic traffic network model, and obtaining the number of vehicles in each region; designing a target function; iteration is carried out in a strategy iteration mode; and introducing a neural network for solving. According to the method, boundary control is carried out on the macroscopic traffic flow in a data driving mode, information in input and output data of a macroscopic fundamental diagram traffic system is fully utilized, and meanwhile, the boundary control quantity of the macroscopic traffic flow is limited; therefore, by adding the saturator into the value function, it can be ensur