Decentralized Semantic Service Discovery in MAS

Service-Oriented Multi-Agent Systems (SOMAS) are dynamic systems populated by heterogeneous agents which can enter or leave the system dynamically. As a consequence of the heterogeneity feature, organizational concepts such as roles are useful to facilitate the coordination in the system. In addition, agent functionality should be modelled as services in order to allow heterogeneous agents or other entities to interact in a standardized way. Furthermore, due to the large-scale and the adaptive needs of the system, the traditional directory facilitators or middle-agents are not suitable for the management of the agents services. In this paper we present a distributed approach for agent service management in SOMAS based on social networks. The proposal provides a fully decentralized structure and allows agents to locate services using only local information. The system is enhanced using semantic information in the generation of the system structure and also in the search process.