Community based parking: Finding and predicting available parking spaces based on the Internet of Things and crowdsensing. (December 2021)

• Record Type: Journal Article
• Authors: Li, Bo; Hou, Fen; Ding, Hongwei; Wu, Hao
• Is Part Of: Computers & industrial engineering. Volume 162(2021)
• Publication Date: 2021-12
• Subjects: Smart parking guidance system -- Crowd Sensing -- Queuing model -- Simulation; Engineering -- Data processing -- Periodicals; Industrial engineering -- Periodicals; 620.00285
• DOI: 10.1016/j.cie.2021.107755
• Languages: English
• ISSNs: 0360-8352

Abstract

Highlights: An innovative two-staged M/M/c/c queuing model proposed for community based parking. The proposed model covers existing models for real-time and steady-state parking. Closed-form solutions derived to predict the availability of parking spaces. Community based parking proved to be effective in diverse parking environments. Abstract: In smart parking guidance systems, the ability to estimate the availability of vacant parking spaces is important to make effective guidance. In this paper, we propose a general architecture for building crowdsensing-based parking guiding system, in which the occupancy state of parking lots can be detected by smart vehicles equipped with sensors and wireless communication devices, or by parking meters and parking fee-paying terminals, and the state information can be used to estimate the probability of finding available spaces for incoming smart vehicles. Five representative scenarios that can be used in such a framework were investigated. The problem to estimate the availability of parking spaces in each scenario was modeled as an M / M / c / c queuing problem with closed-form analytical solutions. The scenarios were validated in a simulation platform and their performance in various parking environments was investigated. Experimental results revealed that the crowdsensing-based parking prediction method can lead to 30.91 % or more relative improvement on average estimation error than steady-state prediction in typical parking environments.