Bus lane simulation optimization method based on proxy-assisted evolutionary algorithm

The invention provides a bus lane simulation optimization method based on an agent-assisted evolutionary algorithm. The method comprises the following steps: S1, establishing a road network simulation model and an optimization mathematical model; s2, collecting an initial simulation sample of a decision variable based on Latin hypercube sampling; s3, establishing an agent model of the simulation model by using the initial simulation sample; s4, obtaining an optimal solution set of decision variables by using an evolutionary algorithm assisted by a proxy model; s5, selecting an optimal solution from the optimized solution set based on an agent model integration method and a sample cutting method; and S6, substituting the most ideal solution into the simulation model for verification and updating the proxy model. Compared with the prior art, the simulation model serves as an evaluation tool of an optimization scheme, and the dynamic evolution process of a traffic system can be simulated; (2) based on a simulati