Are you an EPFL student looking for a semester project?
Work with us on data science and visualisation projects, and deploy your project as an app on top of Graph Search.
This paper studies the routing and charging behaviors of electric vehicles in a competitive ride-hailing market. When the vehicles are idle, they can choose whether to continue cruising to search for passengers, or move a charging station to recharge. The behaviors of individual vehicles are then modeled by a Markov decision process (MDP). The state transitions in the MDP model, however, depend on the aggregate vehicle flows both in service zones and at charging stations. Accordingly, the value function of each vehicle is determined by the collective behaviors of all vehicles. With the assumption of the large population, we formulate the collective routing and charging behaviors as a mean-field Markov game. We characterize the equilibrium of such a game, prove its existence, and numerically show that the competition among vehicles leads to "inefficient congestion" both in service zones and at charging stations.
Christophe Ballif, Alejandro Pena Bello, Noémie Alice Yvonne Ségolène Jeannin, Jérémy Dumoulin
Nikolaos Geroliminis, Emmanouil Barmpounakis
Yuning Jiang, Wei Chen, Xin Liu, Ting Wang