A HYBRID CLONAL SELECTION ALGORITHM FOR QUALITY OF SERVICE-AWARE WEB SERVICE SELECTION PROBLEM

It is imperative to provide service consumers with facilities for selecting required web services according to their Quality of Service (QoS). Several heuristics, which are local adaptation preemptive strategy, elitist perturbation guiding strategy and global tournament strategy for directed local fine-tuning, and a hybrid clonal selection algorithm (CSPLPT) are proposed for QoS-aware web service selection problem. It combines the population-based local search mechanism of clonal selection algorithm and population-based elitist learning mechanism of particle swarm optimization algorithm. The hybridization idea and the efficacy of the proposed strategies are verified and analyzed step by step with web service selection problem. The proposed algorithm CSPLPT is further compared with recent genetic algorithm-based CoDiGA and particle swarm optimization-based iPSOA algorithms with various scales of composite web services. The comprehensive experiments demonstrate the necessity and superiority of the proposed strategies. It also shows that the hybrid algorithm CSPLPT consistently and significantly outperforms CoDiGA and iPSOA in better QoS performance and average evolutionary behaviors while selecting the composite web services with global QoS constraints.