Research on Reliable Path Planning for Intelligent Park-and-Ride Guidance Systems Using an Accelerated Reliability-Bound Convergence Algorithm

Abstract

Park-and-ride (P&R) facilities provide a critical mechanism for integrating private and public transport to alleviate urban traffic congestion. However, their limited capacity leads to substantial uncertainty in parking space availability. Few studies systematically integrate parking space reliability into multi-modal P&R path planning with secondary decision-making upon parking failure. To address this gap, this study proposes a reliable path planning approach for intelligent P&R guidance systems. First, a data-based P&R multi-modal network is constructed to characterize transfers between private car and subway travel modes. Next, a parking guidance model incorporating parking space reliability and utility correlations among travel modes is formulated, in which the secondary decision-making demand is considered. Then, an accelerated reliability-bound convergence algorithm is designed. Finally, a large-scale real-world case study using Beijing P&R data is conducted. The results verify its efficiency and effectiveness, mainly including: (1) Identifying the t-distribution as the optimal distribution for modeling P&R parking space availability; (2) Generating highly reliable multi-modal paths meeting diverse user preferences of cost sensitivity, environmental awareness, and comprehensive reliability; (3) Reducing path iterations from over 30 to no more than 13, thus avoiding exhaustive computation. The study provides reliable insights and practical implications for optimizing intelligent P&R guidance systems.