基于Pareto多目标人工蜂群算法的Web服务组合优化研究
发布时间:2018-05-13 12:18
本文选题:Web服务组合 + QoS ; 参考:《南京财经大学》2014年硕士论文
【摘要】:Web服务是一个崭新的分布式计算模型,能有效地实现网络中数据和信息的集成,是集成技术新的发展方向。由于现在功能相同但QoS不同的Web服务越来越多,这导致了服务的搜索空间不断增大,也使得服务组合问题变得更加复杂。基于此,本文设计了一个Pareto多目标人工蜂群算法来解决服务组合优化问题,主要工作如下:首先,本文给出了一种Pareto解集的构造方法,在解决多目标优化问题时,通常直接比较当前进化种群中每个解的适应度值,最终只产生一个最优解推荐给用户。但在处理Web服务组合这一实际问题时,由于网络中的服务错综复杂,甚至会有一些虚假服务,单个的组合方案很难满足用户的特定需求。所以,本文采用构造当前种群Pareto解集的方式来解决多目标优化问题,最后推荐给用户一组非劣解,以此来更好的解决Web服务组合这一实际问题。接着,本文对蜂群算法进行了改进,原始算法在解的选择阶段采用轮盘赌策略进行解的选择,但这种策略会使算法容易过早收敛,种群的多样性较差。基于此,本文采用Bolzmann策略来改进算法,该策略可使算法的全局搜索能力更好,种群的多样性也能够得到提高。同时,本文对蜜源放弃策略做了相应的调整,对领域搜索公式进行了相应改进,以适应Web服务组合这一实际问题。最后,通过仿真实验验证本文提出的改进方案的可行性。实验表明改进方案可以使种群的多样性增加,有效地避免“早熟”现象,最后产生的组合方案更能满足实际情况中用户需求。从而表明该方法可以更好地处理Web服务组合优化问题。
[Abstract]:Web Services is a new distributed computing model, which can effectively realize the integration of data and information in the network. It is a new development direction of integration technology. Because there are more and more Web services with the same function but different QoS, this leads to the increasing search space of the services and the complexity of the service composition problem. Based on this, a Pareto multi-objective artificial bee colony algorithm is designed to solve the service composition optimization problem. The main work is as follows: firstly, this paper presents a method to construct the Pareto solution set, which is used to solve the multi-objective optimization problem. Usually, the fitness of each solution in the current evolutionary population is directly compared, and only one optimal solution is recommended to the user. However, in dealing with the practical problem of Web service composition, because of the complexity of services in the network and even some false services, it is difficult for a single composition scheme to meet the specific needs of users. Therefore, this paper uses the method of constructing the current population Pareto solution set to solve the multi-objective optimization problem, and finally recommends a group of non-inferior solutions to the user, so as to better solve the practical problem of Web service composition. Then, the bee colony algorithm is improved in this paper. The original algorithm adopts roulette strategy to select the solution in the phase of solution selection, but this strategy will make the algorithm easy to converge prematurely and the diversity of population is poor. Based on this, the Bolzmann strategy is adopted to improve the algorithm. This strategy can improve the global search ability of the algorithm and the diversity of the population. At the same time, this paper adjusts the policy of honey source abandonment and improves the domain search formula to meet the practical problem of Web service composition. Finally, the feasibility of the proposed scheme is verified by simulation experiments. The experimental results show that the improved scheme can increase the diversity of the population, effectively avoid the phenomenon of "precocity", and the resulting combination scheme can better meet the needs of the users in the actual situation. It is shown that this method can better deal with the problem of Web service composition optimization.
【学位授予单位】:南京财经大学
【学位级别】:硕士
【学位授予年份】:2014
【分类号】:TP18;TP393.09
【参考文献】
相关期刊论文 前1条
1 郑金华;蒋浩;邝达;史忠植;;用擂台赛法则构造多目标Pareto最优解集的方法[J];软件学报;2007年06期
,本文编号:1883119
本文链接:https://www.wllwen.com/guanlilunwen/ydhl/1883119.html