多云环境的虚拟应用网络部署决策方法研究  

Research on Deployment Decision Method of Virtual Application Network in Multi-cloud Environment

作　　者：朱华旻[1] 吴礼发[1] 赵鹏 

机构地区：[1]解放军理工大学指挥信息系统学院,南京210007

出　　处：《计算机科学》2017年第B11期286-292,328,共8页Computer Science

基　　金：江苏省自然科学基金项目(BK20131069)资助

摘　　要：多云环境下,用户能够基于虚拟应用技术与基础设施虚拟技术自由组合基础设施资源以部署虚拟应用网络,并且能够快速构建具有一定业务功能的分布式应用系统。鉴于现有多云部署决策方法,以及在部署描述及处理用户多目标需求方面的不足,首先给出了基于开放虚拟格式文档的虚拟应用网络部署描述方法;其次研究定义了基础设施资源组合的常见服务质量指标及多目标优化模型,并使用第二代非支配排序遗传算法(NSGA-II)和多目标粒子群优化(MOPSO)算法求解模型;最后给出了一种基于模糊决策的最终满意解确定方法。多次实验统计表明,两种算法均能在合理时间内实现较好收敛,NSGA-II适合2~3个目标的场景,而MOPSO能够用于更多目标场景,且均有更好表现;模糊决策所得最终解能够最佳匹配用户的目标偏好。In multi-cloud environment, users can freely combine infrastructure resources to deploy vir tual application network based on virtual application technology and infrastructure virtual izat ion technology, and thus quickly bui ld a distributed application system with certain business functions. Regarding the shortcomings of the existing multi-cloud deployment decision-making methods in deployment descriptions and addressing user multi-objective requirements, this paper first presented a deployment description method for the virtual application network based on the open virtual for-mat document. Secondly, the common service qual ity metrics of the infrastructure resource combination were studied, and a multi-objective optimization model of the combination was subsequently defined. Then, the second generation non- dominated sorting genetic algorithm （NSGA-II） and multi-objective particle swarm optimization （MOPSO） algorithm were used to solve the model. Final ly, a fuzzy decision-making method was designed to select the final satisfactory solu-t ion from the obtained results. The statistics of mul tiple experiments show that both algorithms can achieve a good con-vergence wi thin a reasonable time,NSGA-II is only suitable for scenes with 2 to 3 objectives,and MOPSO can be used for scenes with more objectives and performs better than NSGA-II. Moreover, the fuzzy decision-making result can match the user’s objective preference best

关 键 词：多云 虚拟应用网络 基础设施服务 多目标优化 模糊决策 

分 类 号：TP393.09[自动化与计算机技术—计算机应用技术]