Abstract

Web services clustering is the task of extracting and selecting the features from a collection of Web services and forming groups of closely related services. The implementation of novel and efficient algorithms for Web services clustering is relevant for the organization of service repositories on the Web. Counting with well-organized collections of Web services promotes the efficiency of Web service discovery, search, selection, substitution, and invocation. In recent years, methods inspired by nature using biological analogies have been adapted for clustering problems, among which genetic algorithms, evolutionary strategies, and algorithms that imitate the behavior of some animal species have been implemented. Computation inspired by nature aims at imitating the steps that nature has developed and adapting them to find a solution of a given problem. In this chapter, we investigate how biologically inspired clustering methods can be applied to clustering Web services and present a hybrid approach for Web services clustering using the Artificial Bee Colony (ABC) algorithm, K-means, and Consensus. This hybrid algorithm was implemented, and a series of experiments were conducted using three collections of Web services. Results of the experiments show that the solution approach is adequate and efficient to carry out the clustering of very large collections of Web services.

Keywords: artificial bee colony, K-means, Consensus, hybrid algorithms, Web services clustering, semantic similarity measures
