Urban rail transit path connection planning method based on federated learning and computer immune algorithm

The significance of urban rail transit path connection planning lies in optimizing network efficiency, enhancing passenger mobility, and promoting sustainable urban development, ensuring seamless and efficient transportation services. In order to overcome the problems of long and time-consuming traditional path connection planning methods, this paper proposes an urban rail transit path connection planning method based on federated learning and computer immune algorithm. Firstly, design the architecture of the federated learning system, construct a travel time matrix for the transportation network, and estimate the weights for future times. Then, time-varying travel time and distance between demand points are introduced for modeling, and computer immune algorithms are used for solving to optimize path connection. The results show that the selection of vehicle models has a greater impact on demand response and connecting bus route planning. After planning, the path length is only 132km and the number of transfers is only 8, indicating that the method proposed in this paper can improve the effectiveness of traffic path connection planning.