基于改进混合粒子群算法的服务动态选择方法  

A Web service dynamic selection method based on improved hybrid particle swarm optimization algorithm

作　　者：舒振[1] 陈洪辉[1] 罗雪山[1] 

机构地区：[1]国防科技大学信息系统工程重点实验室,湖南长沙410073

出　　处：《中南大学学报（自然科学版）》2011年第10期3086-3094,共9页Journal of Central South University:Science and Technology

基　　金：国防预研重点基金资助项目(9140A06020407KG0127);国家自然科学基金资助项目(70601036)

摘　　要：针对服务组合过程中的服务动态选择问题,建立带约束的Web服务组合QoS全局优化问题的描述模型,分析当前已有各种算法的缺陷和不足,提出一种改进混合粒子群算法的求解方法,并从可行性、有效性以及运行效率3个方面进行仿真实验。研究结果表明:改进的混合粒子群算法综合利用了群体自身信息、局部较优信息、全局较优信息以及遗传算法的交叉、变异、选择等操作对粒子进行更新,增强了粒子群的搜索空间和搜索效率,可以较好地解决服务组合中服务的动态选择问题。Aiming at the Web service dynamic selection problem during Web service composition,a model of the whole QoS（quality of service） optimize problem of Web service composition with restriction was established,the current research of mathematical solving algorithms for solving the model were analyzed,and an improved hybrid particle swarm optimization algorithm was put forward to solve the model.Finally,comprehensive experiments based on simulation case was set up.The results show that in the improved hybrid particle swarm optimization algorithm,the new particle is refreshed by particle information self,optimal solutions of population and individual,the cross,mutation and selection operators of genetic algorithm.The algorithm is feasibile,valid and efficient and it is proved that the algorithm can resolve the whole QoS optimize problem of web service composition efficiently.

关 键 词：WEB服务 粒子群算法 遗传算法 服务动态选择 服务质量(Qos) 

分 类 号：TP39[自动化与计算机技术—计算机应用技术]