Multiagent System-Based Near-Real-Time Trajectory and Microscopic Timetable Optimization for Rail Transit Network

In the rail transit field, the practical operation process suffers from potential energy waste caused by disturbances. The present paper proposes a multiagent system (MAS) to reduce rail transit energy consumption when disturbances occur. The system is able to optimize speed trajectory and microscopic timetable for each train in near real time when disturbances occur. Two case studies have been carried out to investigate the feasibility and efficiency of the proposed methodology. In the first case study, three trains are simulated with 1,212 different scenarios with a disturbance that comes from the leading train. The results of those scenarios show that the proposed system is able to guarantee safety and has good potential in reducing energy consumption in such conditions. In the second case study, a train running among seven stations with potential delays is simulated. The result shows that each train agent can support a microscopic timetable optimization in near real time and results in a 13.40% energy savings. An additional 2,340 scenarios are simulated, and an average of 4.12% energy savings is achieved.