Journal
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
Volume 21, Issue 5, Pages 2167-2179Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TITS.2019.2916337
Keywords
Pricing; Games; Vehicle dynamics; Stochastic processes; Vehicles; Monte Carlo methods; Heuristic algorithms; Parking utilization; dynamic pricing; Monte Carlo tree search; look-ahead model; stochastic; bi-level; integer program
Ask authors/readers for more resources
Excessive search for parking spots in congested areas contributes to additional travel delays and negative socio-economic impacts. While managing parking utilization to address the agency's objectives, it is often very beneficial to reflect the diversity of users' behaviors and their travel choices. This paper develops a stochastic dynamic parking management model, under competitive user-agency perceptions and uncertain user demand and parking occupancy, to simultaneously minimize the total travelers' costs and maximize the parking agency's revenue. The problem is formulated into a dynamic programming model and solved using a stochastic look-ahead technique based on the Monte Carlo tree search algorithm to determine optimal actions on parking price assignment and spot utilization over time. The numerical experiments on a hypothetical and empirical case study are conducted to show the performance of the proposed algorithm and to draw managerial insights. The results are compared with those of benchmark algorithms, which indicate that the proposed methodology can determine near-optimal solutions efficiently.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available