基于知识的人工蜂群服务组合优化算法

Artificial Bee Colony Algorithm for Service Composition Based on Knowledge

近年来,Web服务组合问题一直是研究热点,是典型的NP难题。随着Web服务技术的发展,用户更加注重服务质量。目前,将人工蜂群算法应用于连续性优化问题的研究比较多,然而将其用于解决Web服务组合这一离散化问题却不多见。为了提高在大量Web服务中快速有效找到针对特定问题的最优Web服务组合的效率,以满足用户对服务质量日益提高的需求,文中提出一种基于服务顺序知识的人工蜂群算法(KABC)来解决这一NP问题。首先,建立了单个服务的Qo S评估模型,并提出了应用于Web服务组合优化问题的Qo S数学模型。其次,算法运用当前较优解的服务顺序知识来指导后续解的更新,加快了算法的收敛速度,提高了精度。实验结果表明,与原始的ABC、PSO算法相比较,KABC具有更快、更优的搜索能力以及更好的求解质量。

Web service composition,as a NP hard problem,has always been a hot research in recent years. With the development of Web service technology,users pay more attention to quality of service. Many researches on Artificial Bee Colony（ ABC） are carried out to solve continuous optimization problems. It is rare for using ABC to tackle the Web Service Composition Problem（ WSCP） of discrete optimization. In order to improve the efficiency of finding the best service composition,a Knowledge- based Artificial Bee Colony（ KABC） algorithm is proposed and applied to WSCP. Firstly,the Qo S model of a single Web service and mathematics model of a service composition are built. Secondly,the knowledge of service sequence of the high quality solutions is used to guide the updating of next generation solutions,so as to accelerate the convergence speed and improve the precision of solutions. Experiment shows that compared with original ABC and PSO,KABC has a better performance on WSCP.