Case Study on Web Service Composition Based on Multi-Agent System

Rapid development of the Internet and increasing number of available Web services has generated a need for tools and environments facilitating automated composition of atomic Web services into more complex Web processes. However ,reasoning optimization and utilization in such AI related solutions is still an open problem .In this paper, we proposed a novel multi-agent based semantic web service composition model(SWSCPA) which exploits the relationships among different service consumers and providers, together with the corresponding optimization approach to strengthen the effectiveness of Web service composition. We argue that agents and web services are distinct. In our work, agents provide a distinctive additional capability in mediating user goals to determine service invocations. Through the model, an optimization method was proposed based on the substitute relationship and the dependency relationship. The case study and experimental analysis demonstrates the capability of the proposed approach.