Train Operation Strategy Optimization of Virtual Coupling: A Cooperative Game Based Approach

Authors:

Abstract
Virtual coupling is a recently introduced concept to achieve flexible and on-demand train operations. One of the main challenges in maximizing the throughput of the network is to couple trains on-the-fly efficiently at junctions. This paper presents a novel game based operation strategy optimization approach for virtual coupling trains to solve this problem. A cooperative game model representing trains coupling at junctions is first built. Due to the discrete and high-dimension characteristics of the model, the optimal solution problem has NP complexity. To find optimal operation strategies in large scale models in a reasonable time, we propose an improved particle swarm optimization algorithm by introducing self-adaptive parameters. This paper compares the strategy of train coupling at junctions generated by the proposed method with a naive strategy. The results show that the operation time is reduced by using the cooperative game based optimization approach.
Funding Information
  • National Key Research and Development Program of China (2018YFB1201501)
  • Beijing Natural Science Foundation (L201004)

This publication has 15 references indexed in Scilit: