Predictive Vehicle Repositioning for On-Demand Ride-Pooling Services

TL;DR

This paper introduces a predictive rebalancing algorithm for ride-pooling services that improves fleet utilization, reduces customer wait times, and increases service efficiency through demand forecasting and simulation-based repositioning.

Contribution

A novel demand prediction and simulation-based repositioning algorithm that outperforms existing methods in ride-pooling fleet management.

Findings

Increases service rate and vehicle revenue hours by ~50%.

Serves more customers and reduces waiting times.

Operates efficiently within seconds for large-scale scenarios.

Abstract

On-Demand Ride-Pooling services have the potential to increase traffic efficiency compared to private vehicle trips by decreasing parking space needed and increasing vehicle occupancy due to higher vehicle utilization and shared trips, respectively. Thereby, an operator controls a fleet of vehicles that serve requested trips on-demand while trips can be shared. In this highly dynamic and stochastic setting, asymmetric spatio-temporal request distributions can drive the system towards an imbalance between demand and supply when vehicles end up in regions with low demand. This imbalance would lead to low fleet utilization and high customer waiting times. This study proposes a novel rebalancing algorithm to predictively reposition idle fleet vehicles to reduce this imbalance. The algorithm first samples artificial requests from a predicted demand distribution and simulates future fleet states to identify supply shortages. An assignment problem is formulated that assigns repositioning trips considering multiple samples and forecast horizons. The algorithm is implemented in an agent-based simulation framework and compared to multiple state-of-the-art rebalancing algorithms. A case study for Chicago, Illinois shows the benefits of applying the repositioning strategy by increasing service rate and vehicle revenue hours by roughly 50% compared to a service without repositioning. It additionally outperforms all comparison algorithms by serving more customers, increasing the pooling efficiency and decreasing customer waiting time regardless of the forecasting method applied. As a trade-off, the computational time increases, but with a termination within a couple of seconds it is still applicable for large-scale real world instances.