网络功能虚拟化环境中大规模资源状态监测策略 |
| |
作者姓名: | 海梅生 伊鹏 江逸茗 谢记超 |
| |
作者单位: | 国家数字交换系统工程技术研究中心,河南 郑州 450002 |
| |
基金项目: | 国家重点研发计划基金资助项目(2018YFB080400);国家自然科学基金资助项目(61521003);国家自然科学基金资助项目(61572519) |
| |
摘 要: | 在网络功能虚拟化(NFV)环境中,为了提高网络中基础设施资源利用率,高效动态部署服务功能链,编排管理域需要对网络中底层资源及虚拟网络功能状态进行实时监测,但实时监测会产生大量通信开销。提出了网络通信开销最小化的智能分布式监测策略,通过改进的标签传播算法智能划分子网并选择代理监测节点,实现了对资源和虚拟功能状态的高效监测,并使监测信息通信开销最小。仿真结果表明,所提监测策略使网络中监测信息通信开销降低约13%。图4 不同算法下子网节点数量方差图
|
关 键 词: | 网络功能虚拟化 监测 通信开销 代理节点 |
Large-scale resource state monitoring strategy in network function virtualization environment |
| |
Authors: | Meisheng HAI Peng YI Yiming JIANG Jichao XIE |
| |
Affiliation: | National Digital Switching System Engineering &Technology Research Center,Zhengzhou 450002,China |
| |
Abstract: | In order to improve the utilization of the infrastructure resource and efficiently deploy the service function chain dynamically in network function virtualization,the orchestration management domain needs to monitor the network resources and virtual network function status in real time,but real-time monitoring will bring large communication overhead.An intelligent distributed monitoring strategy with minimal network communication overhead was proposed.The improved label propagation algorithm intelligently subnets and selects agent monitoring nodes to achieve efficient monitoring of resource and virtual function status and minimize monitoring information communication overhead.The simulation results show that the monitoring strategy proposed reduces the monitoring information communication overhead in the network by about 13%. |
| |
Keywords: | network function virtualization monitoring communication overhead agent node |
|
| 点击此处可从《》浏览原始摘要信息 |
|
点击此处可从《》下载全文 |