Scalable Semantic Brokering over Dynamic Heterogeneous Data Sources in InfoSleuthTM

InfoSleuth is an agent-based system for information discovery and retrieval in a dynamic, open environment. Brokering in InfoSleuth is a match-making process, recommending agents that provide services to agents requesting services. This paper discusses InfoSleuth’s distributed multibroker design and implementation. InfoSleuth’s brokering function combines reasoning over both the syntax and semantics of agents in the domain. This means the broker must reason over explicitly advertised information about agent capabilities to determine which agent can best provide the requested services. Robustness and scalability issues dictate that brokering must be distributable across collaborating agents. Our multibroker design is a peer-to-peer system that requires brokers to advertise to and receive advertisements from other brokers. Brokers collaborate during matchmaking to give a collective response to requests initiated by non-broker agents. This results in a robust, scalable brokering system.