A Reasoning Infrastructure to Support Cooperation of Intelligent Agents on the Semantic Grid

Can a knowledge level layer be individuated in the Semantic Grid infrastructure? Is it possible to design a knowledge level ACL which enable agents to cooperate in a geographically distributed Semantic Grid despite failures or malfunctions of nodes? This paper tries to address the above Semantic Grid challenges presenting an Agent-based Open Service Architecture which integrates geographically distributed agents in a Semantic Grid. The architecture is well integrated with standard Internet components and technologies and supports communication among knowledge level agents. The role of agents is to retrieve, execute and compose available services providing more sophisticated instances of them. Inter-agent communication is realized exploiting an advanced agent communication language which supports a fault-tolerant anonymous interaction protocol and satisfies a set of well defined knowledge-level programming requirements. We present the design of the architecture and its implementation, and we highlight the features of the agent communication language by means of a case study, comparing it with current Grid programming technologies. The main advantage of our approach is to demonstrate that different issues, such as high-level inter-agent communication and fault tolerance, can be successfully integrated in Grid infrastructures which provide Web Services maintaining a clean design of the architecture and a knowledge level characterization