基于QoS多目标优化的组合服务执行路径的选择  

The QoS-Based Multi-Objective Optimization Algorithm of the Composite Service Execution Path

作　　者：李滢[1,2] 童维勤[1] 亢朝峰 支小莉[1] 

机构地区：[1]上海大学计算机科学与技术学院,上海200072 [2]南京晓庄学院数学与信息技术学院,江苏南京211171 [3]中兴通讯,江苏南京200012

出　　处：《南京师大学报（自然科学版）》2012年第3期125-133,共9页Journal of Nanjing Normal University(Natural Science Edition)

基　　金：国家自然科学基金(60573109);上海市科技创新行动计划项目(11511500200)

摘　　要：针对目前启发式算法求解组合服务执行路径中存在的不足,将组合服务执行路径上节点服务的QoS多目标优化问题转化为蚂蚁从巢穴到食物之间的最短路径选择问题,提出基于改进的蚁群算法———蚁群系统作为优化工具,并提出了用于屏蔽执行路径结构的虚拟抽象服务的概念,设计了算法中的局部与全局更新规则,将多目标优化的QoS约束参数融入dij参数的定义中,最后通过仿真实验验证了算法的可行性与优越性.In this paper, after discussing the limitations of heuristic algorithm using for composite service execution path optimization, an optimization algorithm of Ant Colony System based on Ant Colony Algorithm is proposed. The algorithm regards the optimization problem as the shortest path solving problem of ant foraging from nest to food. In order to overcome the lack of Ant Colony System only using to solved sequential organization path, a concept of virtual abstract serv- ice was put forward innovatively to shield the different path structures, then local and global updating rules had been redesigned and the constrained QoS parameters were also into the definition of parameter. Finally, through simulation and comparing with basic Ant Colony Algorithm experimental verified the usability and superiority of the algorithm.

关 键 词：QOS 多目标优化 PARETO解集 蚁群系统 虚拟抽象服务 

分 类 号：TP311[自动化与计算机技术—计算机软件与理论]