No abstract

During development of service-based systems (SBS), the quality of services (QoS) plays an important role at helping select more suitable services. There have been several QoS prediction approaches proposed, however, their prediction accuracy is low when there are few historical records in the application environment. In this paper, we propose a new QoS prediction method based on a virtual platform methodology. The method first constructs a virtual platform based on Gaussian distribution regarding stability and performance of services. With the platform, a referral-based QoS prediction method has been developed to improve prediction accuracy. The experimental results indicate that our method outperforms previous approaches, achieving higher prediction accuracy, especially when there are few historical records available.