An Adaptive Solution for Web Service Composition

Dynamic Web service composition is challenging problem and has been intensively investigated in recent years. Nevertheless, most of existing approaches do not provide satisfactory composition results, especially when confronted with a large scale of services. In this paper, we present a novel algorithm called HRLPLA for composing Web services. The algorithm considers functional properties and QoS properties simultaneously. By using hierarchical reinforcement learning, it can deal with large scales of services and generate efficient service compositions. Moreover, the algorithm is suitable for composing Web services in dynamic environment, as reinforcement learning his highly adaptive. We conducted experimental study to verify the effectiveness and efficiency of our method in dynamic service composition.