A QoS-Aware Clustering Based Multi-Layer Model for Web Service Selection

Abstract

The rapid proliferation of new web services over the last decade has led to an increase in functionally identical services, making the service selection system more challenging. In this work, we propose a web service selection model consisting of two layers, which we call CPSky. The upper layer, called the Prefilter layer, filters and allows only potent services to participate in the selection process. Pruning and clustering based on the quality of service form the basis of prefiltering. The bottom layer, called the Selection layer, uses the proposed Skyline-Plus approach to select the appropriate web service. The existing skyline technique always generates the same set of skyline services and does not consider the end-user requested QoS. Additionally, the skyline results in a non-dominated set of services without any ordering of services. To address these issues, we propose a modified skyline, which we call Skyline-Plus. The Selection layer also identifies replaceable web services using the Pearson correlation coefficient. The proposed approach's efficacy is validated through experimental evaluation on a real-world dataset using four performance evaluation parameters. The experimental results show that the proposed approach performs better than existing similar approaches in terms of efficiency and end-user satisfaction.