Research on urban rail line planning methods for smart cities based on big data and forbidden search algorithm

At present, traditional transportation route planning mainly relies on geographical drawings for rough planning and determines the final plan based on field visits, which leads to poor planning results due to the lack of effective identification of traffic demand points. For this reason, an urban rail transit route planning method based on big data and a forbidden search algorithm is proposed. Firstly, we analyze the factors affecting the arrangement of urban rail transit feeder bus stops, determine the bus demand points by calculating the passenger flow demand, construct a two-level dynamic planning model by combining the taboo search algorithm, and establish neighborhood transformation rules to solve the model. Finally, experiments are conducted to verify the planning performance of the proposed method. The results show that the routing scheme planned by the method has fewer inflection points and the planning performance is more satisfactory.