A Clustering-Based QoS Prediction Approach for Web Service Recommendation

The rising popularity of service-oriented architecture to construct versatile distributed systems makes Web service recommendation and composition a hot research topic. It's a challenge to design accurate personalized QoS prediction approaches for Web service recommendation due to the unpredictable Internet environment and the sparsity of available historical QoS information. In this paper, we propose a novel landmark-based QoS prediction framework and then present two clustering-based prediction algorithms for Web services, named UBC and WSBC, aiming at enhancing the QoS prediction accuracy via clustering techniques. Hierarchical clustering is adopted based on the real-word Web service QoS dataset collected with PlanetLab1, which contains response-time values of 200 distributed service users and 1,597 Web services. The comprehensive experimental comparison and analysis show that our clustering-based approaches outperform other existing methods.