Date of Award

December 2018

Degree Type

Dissertation

Degree Name

Doctor of Philosophy

Department

Engineering

First Advisor

Yue Liu

Committee Members

Jie Yu, Xiao Qin, Chao Zhu, Lingqian Hu

Keywords

deep learning, evaluation, logic programming, microscopic simulation, parking

Abstract

The parking industry produces an enormous amount of data every day that, properly analyzed, will change the way the industry operates. The collected data form patterns that, in most cases, would allow parking operators and property owners to better understand how to maximize revenue and decrease operating expenses and support the decisions such as how to set specific parking policies (e.g. electrical charging only parking space) to achieve the sustainable and eco-friendly parking.

However, there lacks an intelligent tool to assess the layout design and operational performance of parking lots to reduce the externalities and increase the revenue. To address this issue, this research presents a comprehensive agent-based framework for microscopic off-street parking system simulation. A rule-based parking simulation logic programming model is formulated. The proposed simulation model can effectively capture the behaviors of drivers and pedestrians as well as spatial and temporal interactions of traffic dynamics in the parking system. A methodology for data collection, processing, and extraction of user behaviors in the parking system is also developed. A Long-Short Term Memory (LSTM) neural network is used to predict the arrival and departure of the vehicles. The proposed simulator is implemented in Java and a Software as a Service (SaaS) graphic user interface is designed to analyze and visualize the simulation results. This study finds the active capacity of the parking system, which is defined as the largest number of actively moving vehicles in the parking system under the facility layout. In the system application of the real world testbed, the numerical tests show (a) the smart check-in device has marginal benefits in vehicle waiting time; (b) the flexible pricing policy may increase the average daily revenue if the elasticity of the price is not involved; (c) the number of electrical charging only spots has a negative impact on the performance of the parking facility; and (d) the rear-in only policy may increase the duration of parking maneuvers and reduce the efficiency during the arrival rush hour. Application of the developed simulation system using a real-world case demonstrates its capability of providing informative quantitative measures to support decisions in designing, maintaining, and operating smart parking facilities.

Available for download on Monday, January 04, 2021

Share

COinS