Intelligent parking management for sustainable society: A data-driven demand elasticity incentive model

Growing urban populations and increased vehicle ownership exacerbated parking shortages, leading to severe congestion and environmental impacts. Consequently, optimal parking allocation becomes a critical challenge for intelligent parking management systems when parking facilities approach capacity during peak demands. To address this issue, we propose an intelligent parking system that employs an incentive-based demand distribution strategy to maximize parking space utilization and mitigate peak-demand congestion. Specifically, a data-driven demand elasticity-based incentive model is designed to influence user behavior and efficiently distribute parking demand via optimal allocation. The system operates a demand response (DR) incentive program that proactively controls incoming vehicle flow via incentives and alternative parking options, smoothing peak demand. This program offers various benefits to parking users, such as access to better parking spots and balancing parking loads between peak and off-peak periods while maintaining user satisfaction. This approach utilizes multi-attribution decision-making (MADM) to operate innovative traffic distribution systems. Incorporating demand elasticity allows the model to quantify drivers’ responsiveness to incentives, enabling dynamic adjustments of demand distribution that improve parking space utilization and prevent over-saturation peak times. We evaluate the proposed system by simulation experiments considering a real parking lot in Gunma, Japan, where it alleviates peak parking congestion, reduces the time spent searching for spaces, and lowers parking delays, fuel consumption, and CO${}_2$ emissions compared to conventional parking systems. The proposed system enhances parking efficiency and contributes to sustainable urban parking management by encouraging users to shift to off-peak hours.