2013 Hilaire, Vincent and Cossentino, Massimo and GECHTER, Franck and Rodriguez, Sebastian and Koukam, Abderrafiaa, An approach for the integration of swarm intelligence in MAS: an engineering perspective, Expert Systems with Applications, 40(4): 1323–1332, 2013.
Resumen: For more than 20 years, researchers have designed models in order to describe swarm intelligence and apply the resulting techniques to complex problems. However, there is still a gap between these models and current MAS methodologies. The goal of this paper is to propose a principled and methodological approach for the engineering of systems based upon swarm intelligence. The constraints are, on the one hand, to enable the analysis, design and implementation of such systems; and, on the other hand, to formally analyze and verify properties of resulting systems. The principles of the approach are based, on the one hand, on requirement driven activities that produce goals to be fulfilled by the system of interest and, on the other, hand on an ontological modeling of the problem domain. This ontological modeling conceptualizes the phenomenon one seek to imitate and thus allows it understanding. The produced ontology is refined through the methodology activities down to organizational models. In mainstream software engineering most methodologies use requirements only to drive their initial activities. It is also the case for several MAS design approaches. These requirements are refined down to agents that fulfill them. However, these techniques do not cover all possible MAS. Indeed, swarm approaches are based on the replication of existing behaviors, that have produced in certain experimental conditions the desired emerging properties. In order to engineer such kind of MAS, we propose to use instead of requirements only driven activities an approach based on requirements and ontological modeling of the problem domain. The principle is to produce an ontology which conceptualizes the problem. The interacting entities the designer want to replicate and their possible actions are part of this ontology. Some guidelines are provided in order to identify organizations and roles from this ontology. This activity is integrated in an existing methodology, namely ASPECS. An example of analysis of a localization and tracking system based upon a swarm approach is given.