Hybrid genetic algorithm for selecting the optimal or near-optimal solution in semantic Web service composition

This paper presents a hybrid bio-inspired algorithm that selects the optimal or a near-optimal solution in semantic Web service composition. The proposed algorithm combines principles from evolutionary computing, tabu search and monkey search to optimize the selection process in terms of execution time and explored search space. In our approach, the search space is modeled as an Enhanced Planning Graph structure which encodes all the possible composition solutions for a given user request. To establish whether a solution is optimal, the QoS attributes of the services involved in the composition as well as the semantic similarity between them are considered as evaluation criteria. The proposed selection algorithm has been integrated in an experimental framework and a set of experiments has been carried out on different Enhanced Planning Graph topologies. The performance evaluation of the proposed algorithm has been done using the fitness graph and population diversity evolutionary measures.