Combining quantitative constraints with qualitative preferences for effective non-functional properties-aware service composition

With the increasing popularity of the service-oriented architecture and web service technologies, service composition has become widely adopted to create value-added services from existing ones. As more web services have been deployed on the Internet, it results in a large number of services providing identical functionalities while differing in their non-functional properties (NFPs). However, most of the existing techniques for NFP-aware service composition only consider quantitative NFPs. In this paper, we present a model that deals with both quantitative and qualitative NFPs. We develop two algorithms, where the first one combines global optimization with local selection and the second one leverages a genetic algorithm. We have conducted extensive experiments to evaluate the effectiveness of our model and algorithms.