面向网络服务的云数据中心仿真系统的设计与实现

发布时间：2018-05-08 19:43

本文选题：网络服务 + 云数据中心　；参考：《北京邮电大学》2016年硕士论文

【摘要】：随着网络服务的蓬勃发展,服务选择方法成为重要的研究热点。而随着云数据中心的发展,大量网络服务部署在云数据中心上,服务选择不可避免的将受数据中心底层性能的影响,进而影响服务组合性能。现有的国内外大部分仿真测试软件都只能用于网络层及以下各层的验证,尚未有能支持跨层感知和协同的仿真系统。此外,目前的仿真系统无法实现网络服务组合和选择对云数据中心底层相关参数的感知。为此,针对网络服务选择的跨层感知仿真需求,论文设计和开发了一个面向网络服务的云数据中心仿真系统。该系统不仅可以对云数据中心的各种实体进行建模和仿真,还可以完成对云数据中心网络拓扑、网络时延、任务执行、动态调度等特性进行仿真,保证网络服务能够全面获取云数据中心的底层环境状态。论文通过对网络服务关键算法进行研究,提出了一种网络感知服务选择算法,并根据算法仿真的需求,确定了基于开源云计算平台CloudSim进行二次开发,实现云数据中心仿真系统的基本技术路线。然后,根据服务选择算法的网络感知要求,设计了云数据中心仿真系统体系结构,设计了各个模块之间的服务接口与交互流程,并完成了仿真系统功能实现与测试。论文最后基于云计算中心仿真系统对论文提出的网络感知服务选择算法进行了仿真,验证了算法的有效性和仿真系统的功能性。论文最后总结了相关工作,并提出了下一步的研究方向。
[Abstract]:With the rapid development of network services, service selection has become an important research hotspot. With the development of cloud data center, a large number of network services are deployed in the cloud data center. Service selection will inevitably be affected by the underlying performance of the data center, and then affect the performance of service composition. Most of the existing simulation and testing software at home and abroad can only be used for the verification of the network layer and the following layers, but there is no simulation system that can support cross-layer awareness and collaboration. In addition, the current simulation system can not realize the network service composition and selection of the cloud data center underlying related parameters perception. In order to meet the requirement of cross-layer perceived simulation for network service selection, a cloud data center simulation system for network service is designed and developed in this paper. The system can not only model and simulate all kinds of entities in cloud data center, but also simulate the network topology, network delay, task execution and dynamic scheduling of cloud data center. To ensure that the network services can fully access the underlying environment of the cloud data center state. Through the research on the key algorithms of network service, this paper proposes a network aware service selection algorithm, and according to the needs of algorithm simulation, determines the secondary development based on open source cloud computing platform CloudSim. The basic technical route of cloud data center simulation system is realized. Then, according to the network awareness requirements of the service selection algorithm, the architecture of the cloud data center simulation system is designed, the service interface and interaction flow between the modules are designed, and the function of the simulation system is realized and tested. Finally, based on the cloud computing center simulation system, the proposed network aware service selection algorithm is simulated, which verifies the effectiveness of the algorithm and the functionality of the simulation system. Finally, the paper summarizes the related work, and puts forward the next research direction.
【学位授予单位】：北京邮电大学
【学位级别】：硕士
【学位授予年份】：2016
【分类号】：TP393.09;TP391.9

【参考文献】