Agent-based Model to Web Service Composition

Traditional centralized Web Service Composition (WSC) approaches suffer from critical problems such as performance bottleneck and single point of failure. However, the analogy between Service and Agent Computing paradigms suggests that incorporating both technologies will likely lead to a more effective hybrid service model. In this work, we adopt an agent-based approach to WSC, in which Service Dependency Graph (SDG) is constructed as an AND/OR graph, distributed among the agent community members. Upon receiving a user composition request, agents perform internal reasoning and corporate through a communication protocol attempting to find a solution. Experiments are conducted on a public dataset and results show the effectiveness of the proposed approach in terms of communication cost.