Models for integration with parallelism of distributed organizations
Abstract
Distribution has become a common characteristic of modern service and production systems. Enterprises rely on it for provision of their supplies, labor, and for selling their products in increasingly dynamic global markets. This research proposes a model for fast evaluation of distributed organizations, the optimization of their integrated operation, and analysis of the distributed assignment of the integrated tasks. The method developed, called the Distributed Parallel Integration Evaluation Model (DPIEM) generates a logical integrated model of the distributed tasks based on three integration scenarios. DPIEM minimizes the integrated tasks total cost by adding as many parallel servers per task as possible. The total cost comprises the integrated enterprise operational cost and the average server load cost, including the latter the communication from coordinating the task execution and the cost of the parallel servers used by the integrated enterprise. In its last step, DPIEM analyzes the cost for assigning the integrated tasks to the distributed environment. The DPIEM model was tested for three cases: (1) assembly, including the distributed assembly of two part-types; (2) sales and production, including the coordination of Sales and Production Centers to satisfy the demand for two part-types; and (3) design tasks, including the Iterative Design Model (IDM) for the design of certain bicycle components. A total of 9 scenarios for these three cases were analyzed by DPIEM, yielding the recommended number of parallel servers per integrated task. For comparison, simulations of the scenarios with the TIE parallel-computer environment were developed. The TIE simulation results corroborate the DPIEM recommendations based on the lowest total cost for each of the three cases. The research concludes with the evaluation of the DPIEM advantages and limitations.
Degree
Ph.D.
Advisors
Nof, Purdue University.
Subject Area
Industrial engineering
Off-Campus Purdue Users:
To access this dissertation, please log in to our
proxy server.