AI Planning for Web Service Automatic Composition Using Petri Nets

This paper presents an AI planning method for Web service automatic composition using Predicate/Transition (Pr/T) net model. First, based on Web service description of inputs, outputs, preconditions and effects in OWL-S specification, a Pr/T net model is constructed for a service composition plan. Then, this plan is effectively solved by a reachability algorithm of the Pr/T net and a corresponding reachability graph is obtained. Moreover, a regular language of Pr/T net is generated for representing all plan paths of a service composition. Finally, a process model of composite service is extracted after normalization of the plan paths. This method provides a complete solution from modeling AI plan to constructing process model for service composition, so it is helpful for realizing automatic composition and dynamical integration of Web service.

1 Introduction

Web service composition has recently taken a central stage as an emerging research area, and several techniques have been proposed in this area ^[1]. Among these techniques, Al planning related service composition techniques can generate a composition plan automatically, locate the correct services dynamically, and adapt dynamic characteristics of services to satisfy the increasing changeable requirement of business applications. Hence, this trend has triggered a great number of research efforts on the composition of Web services both in academia and in industry^[2].