TY - JOUR
T1 - MDN-Enabled SO for Vehicle Proactive Guidance in Ride-Hailing Systems: Minimizing Travel Distance and Wait Time
AU - Li, Xiaoming
AU - Gao, Jie
AU - Wang, Chun
AU - Huang, Xiao
AU - Nie, Yimin
PY - 2023
Y1 - 2023
N2 - Vehicle proactive guidance strategies are used by ride-hailing platforms to mitigate supply–demand imbalance across regions by directing idle vehicles to high-demand regions before the demands are realized. This article presents a data-driven stochastic optimization framework for computing idle vehicle guidance strategies. The objective is to minimize drivers’ idle travel distance, riders’ wait time, and the oversupply costs (OSCs) and undersupply costs (USCs) of the platform. Specifically, we design a novel neural network that integrates gated recurrent units (GRUs) with mixture density networks (MDNs) to capture the spatial-temporal features of the rider demand distribution.
AB - Vehicle proactive guidance strategies are used by ride-hailing platforms to mitigate supply–demand imbalance across regions by directing idle vehicles to high-demand regions before the demands are realized. This article presents a data-driven stochastic optimization framework for computing idle vehicle guidance strategies. The objective is to minimize drivers’ idle travel distance, riders’ wait time, and the oversupply costs (OSCs) and undersupply costs (USCs) of the platform. Specifically, we design a novel neural network that integrates gated recurrent units (GRUs) with mixture density networks (MDNs) to capture the spatial-temporal features of the rider demand distribution.
UR - https://doi.org/10.1109/MSMC.2022.3220315
U2 - 10.1109/MSMC.2022.3220315
DO - 10.1109/MSMC.2022.3220315
M3 - Article
SN - 2333-942X
VL - 9
SP - 28
EP - 36
JO - IEEE Systems, Man, and Cybernetics Magazine
JF - IEEE Systems, Man, and Cybernetics Magazine
IS - 3
ER -