Towards Automated Service Matchmaking and Planning for Multi-Agent Systems with OWL-S - Approach and Challenges.

In the past, the demand for modular, distributed and dynamic computer systems has increased rapidly. In the field of multi-agent systems (MAS) many of the current approaches try to account for these requirements. In this paper we discuss the shortcomings of the semantic service selection component SeMa(2), propose improvements and describe an integration concept into a multi-agent framework. Further, we illustrate how this system can be extended by an automated service composition component using methods from the AI planning community.