Collaborative Workflow Management in Holonic Multi-Agent Systems

Abstract

Holonic multi-agent systems (HMS) provide a flexible architecture to achieve a goal based on dynamic organization and collaboration of autonomous agents. However, the structure of the holons in HMS presents a challenge in the design of an effective mechanism to dynamically organize agents and deliver the relevant information to the right agents at the right time to achieve a goal. How to provide a framework to realize effective human computer interaction in HMS is critical to the success and adoption of HMS. The objectives of this paper are to propose a viable design methodology to achieve effective human computer interaction in HMS based on context-aware computing technology and HMS architecture. Context-aware computing refers to an application’s ability to adapt to changing circumstances and respond based on the context of use. A system is context-aware if it uses context to provide relevant information and/or services to the user at the point of need. To achieve these objectives, we first propose Petri net models to describe the workflows in HMS. Next, we propose models to capture resource activities in HMS. Finally, the interactions between workflows and resources are combined to obtain a complete model for workflow management. Based on the model, we propose architecture to dynamically generate context-aware user interface to guide the users and control resource allocation based on the state of HMS.