Credible and Online QoS Prediction for Services in Unreliable Cloud Environment

With the widespread adoption of cloud computing, Service-Orientated Architecture (SOA) facilitates the deployment of large-scale online applications in many key areas where quality and reliability are critical. In order to ensure the performance of cloud applications, Quality of Service (QoS) is widely used as a key metric to enable QoS-driven service selection, composition, adaption, etc. Since QoS data observed by users is sparse due to technical constraints, previous studies have proposed prediction approaches to solve this problem. However, the dynamic nature of the cloud environment requires timely prediction of time-varying QoS values. In addition, unreliable QoS data from untrustworthy users may significantly affect the prediction accuracy. In this paper, we propose a credible online QoS prediction approach to address these challenges. We evaluate user credibility through a reputation mechanism and employ online learning techniques to provide QoS prediction results at runtime. The proposed approach is evaluated on a large-scale real-world QoS dataset, and the experimental results demonstrate its effectiveness and efficiency in unreliable cloud environment.