A flow optimization approach for the rebalancing of mobility on demand systems

摘要

In this paper, we propose an optimization policy for increasing the utilization level of mobility on demand systems (MOD). The system is modeled through a closed queueing network, on which a suitable parameter identification phase must be executed. We define a measure of imbalance of the system based on customer demand, then we use such measure to cast the problem of the redistribution of vehicles in a flow optimization fashion. Leveraging the model characteristics, we are able to account for a wide range of features of MOD systems, enabling the design of efficient and effective redistribution strategies. Our strategy is validated on datasets provided by the “ToBike” bike sharing system, located in the city of Turin, Italy.