Although Multi Agent Systems (MAS) have attracted a great deal of attention in the field of software engineering, with their promise of capturing complex systems, they remain far away from commercial popularity mainly due to the accessibility of MAS methodologies for commercial developers. In this paper we present a practical method for developing self-managing MAS that we believe enables not only software developers but also business people beyond the academic community to design and develop MAS using familiar concepts. We present the main three phases of the proposed methodology, with details and examples of all the visual models, followed by details of its supporting metamodel, in which we describes the MAS concepts used and their relationships. In particular, the methodology features 1. a formal specification mechanism for system norms 2. offers organizational support of MAS through institutions, and 3. supports self-management explicitly through dynamic planning.
|Number of pages||17|
|Journal||Journal of Scalable Computing: Practice and Experience|
|Publication status||Published - Jun 2012|