An Agent based Supplier Selection Approach

Abstract

Supplier management systems, in addition to the selection of suppliers, also need to respond to changes in supplier base, re-allocation of purchase orders, at an operational/tactical level. Supplier management systems should also aid in strategic decisions such as creation of Acceptable Vendor Lists (AVLs). This research focuses on the design and development of an agent-Based framework that works in a simulation-Based control architecture. Various decision making techniques applied for supplier selection, each having inherent advantages and disadvantages compared to the others. an agent system, which acts as a component of a larger simulation-agent framework that can aid in design, analysis and control of reverse logistics applications is proposed. Extensive literature is available on supplier selection techniques but no one particular approach or solution method is applicable to all domains. Moreover, these models tend to solve strategic decisions and arc often not studied in the context of deriving active control policies. the objective of this agent system is to aid a simulation-Based framework in supplier selection in two modes - analytical mode (long term average solutions) and real time control mode. This agent system will serve as the information gathering mechanism and will interface with the simulation framework and a 'battery' of decision making tools. by separating the information exchange channels from the decision making tools, a plug-and-play environment can be implemented. the decision making tools, modeled as "plug-and-play" components can be used by the agent system to solve the supplier management problem presented to it by the simulation model. a mobile, multi-agent system is being developed for this task. the agent system can be invoked by the simulation framework, based on certain pre-determined triggers (supplier replacement, inventory replenishment, etc.). Depending on the problem that needs to be solved by the agent system, it uses different decision making tools to arrive at the 'best' solution, as required by the user specifications. by incorporating the flexibility of multiple decision making tools (differing in solution technique), the system enables the framework to consider the same problem using different criteria. the research investigates the impact of multiple decision making tools. the initial framework proposed will be used in implementation for studying the impact and responsivencss of different supplier selection techniques in a dynamic environment, while taking primarily operational decisions.

Department(s)

Engineering Management and Systems Engineering

Keywords and Phrases

Agent based system; Simulation-based Control; Supplier Selection

Document Type

Article - Conference proceedings

Document Version

Citation

File Type

text

Language(s)

English

Rights

© 2024 Scimago Journal & Country Rank, All rights reserved.

Publication Date

01 Dec 2004

This document is currently not available here.

Share

 
COinS