IMPROVING THE PRODUCTIVITY OF THE AMERICAN AUTOMOBILE: A STOCHASTIC PROCESS VIEW
Abstract
Statistical analyses of the results of a year-long study into how local citizens utilize their family vehicles are presented and the extent of congruence between observed behavior and theoretical stochastic process distributions is measured. The peak-load features of vehicle demand are recognized as a non-homogeneous queueing process. A mixed-discrete optimization model is proposed to investigate management of an enterprise whose members jointly own a fleet of vehicles. The consumer cost of such an enterprise, when coupled with the use of a personal mini-car, is shown to be substantially less than the cost of owning and operating a personal full-sized car. The optimal number of shared vehicles per member and peak/off-peak price differentials for the enterprise are determined. Scenarios involving alternate enterprise management structures are analyzed by computer model parameter studies.
Degree
Ph.D.
Subject Area
Operations research
Off-Campus Purdue Users:
To access this dissertation, please log in to our
proxy server.