Automated Composition of Semantic Web Services Using Case-Based Planning

One of the most challenging issues of service-centric software engineering is the automatic composition of services. In academia, most approaches reduce the service composition problem to the AI planning problem and generate a plan for the user's request from scratch. However in the real world there may be a large amount of same or similar requests, so how to adapt the existing solutions for the past requests to functionally fit for the current same or similar ones becomes a new challenge in the context of semantic Web services. In our study, we propose an approach for automated composition of semantic Web services based on case-based planning. The generated plan can have sequential and non-sequential control constructs. Additionally, a case study from the bioinformatics domain is given to illustrate our approach.