High-speed Railway Rolling Stock Scheduling Based on ADMM Decomposition Algorithm

With the rapid development of high-speed railways in recent years, the optimization of the rolling stock scheduling has become an important part of transportation organization, which can promote to reduce the number of rolling stocks and improve the efficiency of operation. We take the train timetable as the input condition, adopt the time-space-state network to formulate the optimization problem of rolling stock scheduling, and build the optimization model. The goal is to minimize the total operating time cost of the train, the constraints is the train task assignment unique constraints, flow balance constraints, the first-level maintenance constraints etc. We use the Alternating Direction Method of Multipliers (ADMM) algorithm to solve the model, which is a special case of integer linear programming. The multi rolling stocks scheduling optimization problem is decomposed into the least-cost train path sub-problem of every rolling stock, we solve sub-problems by the improved dynamic programming method. The Beijing-Tianjin high-speed railway instance is tested. We set the value of the lagrange multiplier and the penalty coefficient in ADMM, test this case, and calculate the utilization of every rolling stock. The practicability of the model and algorithm is verified.