| The rapid growth of airport throughput has put a lot of pressure on the airport’s integrated transportation system.As an important public transportation tool,airport buses play a pivotal role in the collection and distribution of airports.However,the current airport bus operation process is greatly affected by urban traffic,the passenger flow is unevenly distributed,and the operation scheduling is not standardized.As a result,the waiting time for passengers is too long,the attraction to passengers is insufficient,and resources are wasted.Aiming at the problem that the influencing factors of the airport bus operation process are complex and the operation time is difficult to predict,an airport bus operation time prediction model based on the subspace identification algorithm is established.According to the multi-source big data generated in the operation process,considering the number of passengers,departure interval,road congestion and other factors in different periods,the state space model of airport bus operation process is established.The characteristic variables suitable for describing the bus operation process are extracted as the input and output of the model,and the model is solved by the subspace identification method,and compared with the BP neural network and the least square method.Based on the prediction of the bus running time,combined with the arrival rate of passengers in the waiting area,the departure time is used as a decision variable.According to the actual operation rules of airport bus,the constraint conditions are established,and the scheduling optimization model is established with the objective of minimizing the weighted average of passenger waiting time and bus operation time.Solve the optimal departure timetable through a hybrid algorithm.Taking the bus operation route of a large hub airport in China as a case for simulation research,the experimental results show that the designed model can predict the operating time of the airport bus well,and the generated optimal scheduling plan is more in line with the passenger flow law.This research can enhance the operating efficiency of airport buses and decrease the waiting time of passengers. |