A Bayesian network based Qos assessment model for service selection

Quality of Service (Qos) plays a key role in web services. In an open and volatile environment, services may not deliver the Qos they declared. Hence, it is important to provide a Qos assessment model to select the most appropriate service for the user. Although many researches have been done to develop models and techniques to assist users in Qos assessment, most of them ignore various Qos requirements of users, which are great important to evaluate providers with different service levels. In this paper, we propose a Bayesian network based Qos assessment model to select the service most suitable to the user. This model can predict the service’s capability in various combinations of users’ Qos requirements. Experimental results show that the proposed Qos assessment model is effective.