A multi-agent framework for coordination and system integration.

摘要

This thesis presents a multi-agent framework for coordination and integration of information systems. By modeling typical enterprise information systems as consisting of multiple agents with different functionalities, the methodology provides the representational formalism, coordination mechanisms, and control schemes necessary for integrating heterogeneous units of an information system while meeting such performance criteria as overall effectiveness, efficiency, responsiveness, and robustness.; The multi-agent framework models each stage or process as an autonomous agent. Message passing among these distributed agents forms the control structure. Each agent has an internal behavior model, a functional component consisting of procedures, heuristics, or strategies, and a protocol for interacting with other agents. The protocols specify what action an agent will take based on its local state and the messages received from other agents. The concurrent execution of the protocols by all the agents determines the coordination mechanism used by the agents and the resulting emergence of their behavior.; The framework is applied to the development of a manufacturing information system for integrating and managing the production processes of a real world manufacturing facility for making printed circuit boards. Performance results confirm that the system integration framework is important to support complex business processes that involve multiple steps of activities processed by a group of agents across a variety of functionalities.