Research On Automated Web Services Composition Based On AI Planning

The growth of Internet technologies has unleashed a wave of innovations that change the way business. Many companies are moving their main operations to the web for more automation, efficient business processes and global visibility. In order to survive the competition created by this new online economy, companies should choose and implement the right software and technology solution. Web Service is a new type of software system to handle EAI (Enterprise Application Integration) and enable improved coordination among multiple computing platforms, applications, and business partners. And Web service composition provides a mechanism to combine different services together to handle more complex business process.Automatic Web services composition can be achieved by using AI planning techniques. HTN planning has been adopted to handle the OWL-S Web service composition problem. However, existing composition methods based on HTN planning have not considered the choice of decompositions available to a problem which can lead to a variety of valid solutions. Moreover, users often want more than one plan to choose and to be given the optimal one. Thus, how to give the better plans is the key issue in Web services composition research area.This paper presents a new Web service composition approach named Markov-HTN which includes two parts. First, improve the decomposing way in HTN to search more solutions to provide users more feasible composition plans. Next, build a MDP model based on HTN planning process to evaluate the optimal plan. Moreover, an approach of solving the conflicts on the basis of Markov-HTN plans is proposed. We implement the Markov-HTN composition method to verify the efficiency of the method. The rusults illustrate that our approach is efficient to find more than one feasible plans and identify the optimal one.