计算机科学
分布式计算
吞吐量
网络服务
计算机网络
服务(商务)
软件部署
网络延迟
资源配置
实时计算
电信
无线
操作系统
经济
网络数据包
经济
作者
Peiying Zhang,Ping Yang,Neeraj Kumar,Mohsen Guizani
出处
期刊:IEEE Transactions on Vehicular Technology
[Institute of Electrical and Electronics Engineers]
日期:2022-07-01
卷期号:71 (7): 7730-7738
被引量:13
标识
DOI:10.1109/tvt.2022.3165145
摘要
Future communication networksrequire higher bandwidth, greater coverage, and better throughput. The Space-Air-Ground Integrated Network (SAGIN) has the advantage of wide-area coverage and can cover global communications. It can meet the needs of network resources for maritime activities and remote mountainous areas, which is of great significance to the realization of a new generation of communications networks. With the development of the network and the emergence of delay-sensitive applications such as the Internet of Things, improving the delay performance of the system has received extensive attention. SAGIN involves multiple networks and is more complex than other networks. If there is no reasonable management between different networks, it is easy to lead to difficult link deployment and high time delay. On the basis of research and customization of SFC technology, it can provide a wide range of services and other advantages. It has significant performance in application scenarios involving multi network integration. In order to solve the above problems, this paper studies the SAGIN architecture of SFC based on business types. A service function chain mapping method based on delays prediction is proposed. Calculate the delay of the deployment path and select the path with the lowest delay as the SFC mapping path. The service model is constructed according to the mapping path, and the network slices are divided based on the service type. The simulation results show that the SFC mapping algorithm based on time delay prediction is compared with the traditional SFC mapping scheme. The algorithm does not affect other indicators, the CPU resource utilization rate is 27.8 $\%$ higher, and the link resource utilization rate is 22.7 $\%$ higher. The service acceptance rate increased by 21.5 $\%$ , the latency performance increased by 38.2 $\%$ , and the total resource consumption is reduced by 25.2 $\%$ .
科研通智能强力驱动
Strongly Powered by AbleSci AI