基于改进粒子群算法的Web服务组合  

Web Service Composition Based on Modified Particle Swarm Optimization

作　　者：温涛[1,2] 盛国军[1,2] 郭权[2] 李迎秋[1,2] 

机构地区：[1]东北大学软件中心,沈阳110819 [2]大连东软信息学院辽宁省网络安全与计算技术重点实验室,辽宁大连116023

出　　处：《计算机学报》2013年第5期1031-1046,共16页Chinese Journal of Computers

基　　金：国家自然科学基金项目(60803131);国家"八六三"高技术研究发展计划项目基金(2007AA04Z103);国家科技支撑计划项目(2009BAH43B02;2009BAH47B06)资助~~

摘　　要：Web服务组合优化问题是典型的NP难题.将PSO算法用于连续性优化问题的相关研究较多,但将其应用于Web服务组合优化问题并不多见.文中提出一种改进的基于子粒子圆周轨道和零惯性权重的MDPSO算法,并将其应用到Web服务组合优化问题中,该算法使用基于三角函数的非线性动态学习因子及种群早熟收敛预测与处理方法控制粒子群的行为,在粒子的局部开拓能力和全局收敛能力之间达到良好的动态平衡.最后文中给出了MDPSO算法的实验及评价方法.这些概念和方法为PSO算法在Web服务组合问题上的应用研究提供了一种全新的思路.通过与传统的PSO算法做比较,验证了该算法在Web服务组合问题上效率更优.通过对实验数据的分析和解释得到了若干有益的结论,为进一步的研究工作奠定了基础.Web service composition optimization is a typical NP-complete problem. PSO algo- rithm is widely used in the research field of continuous optimization, but rarely seen in Web serv- ice composition problem. In this paper, we propose a new modified particle swarm optimization algorithm called MDPSO based on sub-particle circular orbit and zero-value inertial weight, which is applied in Web service composition optimization problem. MDPSO adopts trigonometric-func- tion-based non-linear dynamic learning factors and a prediction method for population premature convergence, which can keep better balance between the local exploring ability and the global converging ability of particles. Finally, a novel algorithm evaluation method is presented in the experiment. These concepts and methods provide a new thinking route for application researches of WSC problem. Experimental results show that MDPSO algorithm can achieve better perform- ance than traditional PSO algorithms in WSC optimization. Some useful conclusions are obtained through the analysis and explanation of the experimental data, which lay a solid foundation for further researches.

关 键 词：WEB服务组合 粒子群优化算法 子粒子圆周轨道 非线性动态学习因子 防早熟收敛 

分 类 号：TP311[自动化与计算机技术—计算机软件与理论]