Optimal Web service composition method based on an enhanced planning graph and using an immune-inspired algorithm

This paper presents a new approach for the automatic composition of semantic Web services based on the AI planning graph technique. In the context of Web service composition we have extended the planning graph with the new concepts of service cluster and semantic similarity link and have adapted and enhanced an immune-inspired algorithm that ranks the composition solutions according to user preferences. The composition algorithm creates a planning graph in a multi-layered process in order to solve the Web service composition request. Within each layer, semantic similarity links between the input parameters of the selected services in the current layer and the output parameters of other services, selected in previous layers, are stored in a matrix of semantic links. The semantic similarity links are calculated by using evaluation measures adapted from information retrieval such as recall, precision and F-measure.