D2Park: Diversified Demand-aware On-street Parking Guidance

To address the increasingly serious parking pain, numerous mobile Apps have emerged to help drivers to find a convenient parking spot with various auxiliary information. However, the phenomenon of "multiple cars chasing the same spot" still exists, especially for on-street parking. Existing reservation-based resource allocation solutions could address the parking competition issue to some extent, but it is impractical to treat all spots as reservable resources. This paper first conducts a qualitative investigation based on the online survey data, which identifies diversified parking requirements involving i) reserved users, who request guaranteed spots with a reservation fee, ii) normal users, who request non-guaranteed spots with a "best-effort" service, and iii) external users, who do not use any guidance service. To this end, we design the D2Park system for diversified demand-aware parking guidance services. We formulate the problem as a novel Heterogeneous-Agent Dynamic Resource Allocation (HADRA) problem, which considers both current and future parking demands, and different constraints for diversified requirements. Two main modules are used in the system: 1) multi-step parking prediction, which makes multi-step parking inflow and occupancy rate predictions given the current parking events data and external factors; and 2) diversified parking guidance, which integrates the cooperation-based and competition-based resource allocation mechanisms based on a model predictive control framework to achieve a better performance balance among different user groups. Extensive experiments with a four-month real-world on-street parking dataset from the Chinese city Shenzhen demonstrate the effectiveness and efficiency of D2Park.