天地一体化智能网络智能节点部署策略  

Deployment Strategy of Intelligent Node in Integrated Intelligent Network

作　　者：杨力[1,2] 何兆斌 孔志翔 YANG Li;HE Zhao-bin;KONG Zhi-xiang(Communication and Network Key Laboratory,Dalian University,Dalian 116622,China;Information and Engineering College,Dalian University,Dalian 116622,China;College of Automation,Nanjing University of Science and Technology,Nanjing 210094,China)

机构地区：[1]大连大学通信与网络重点实验室,辽宁大连116622 [2]大连大学信息工程学院,辽宁大连116622 [3]南京理工大学自动化学院,南京210094

出　　处：《小型微型计算机系统》2022年第1期159-164,共6页Journal of Chinese Computer Systems

基　　金：国家自然科学基金项目(61722105,61931004)资助。

摘　　要：针对传统卫星网络中,由于低轨卫星节点计算能力不足,导致大量计算任务需要传输到高轨卫星计算或转发,进而产生巨大传输时延的问题,本文利用移动边缘计算技术,结合天地一体化智能网络架构,提出了一种基于人工蜂群的智能卫星节点优化部署算法.该算法通过迭代,结合网络分簇算法,选出边缘服务有效覆盖率最高的智能卫星节点部署策略.从而使得更多卫星和地面节点能够获取到边缘服务,进而有效降低了系统的平均传输时延.实验部分建立了基于Matlab和STK的仿真实验平台,仿真结果表明本文提出的算法有效降低了传统卫星网络的平均传输时延,优化效果与粒子群算法和集群化部署算法进行对比,也有着较大的提升.In traditional satellite networks, due to the lack of computing power of LEO satellite nodes, a large number of computing tasks need to be calculated or transmitted by GEO satellites, resulting in huge transmission delay.In this paper, using the mobile edge computing technology, combined with the integration of heaven and earth intelligent network architecture, an intelligent satellite node deployment algorithm based on artificial bee colony is proposed.Through iteration and network clustering algorithm, the deployment strategy of intelligent satellite node with the highest effective coverage rate of edge service is selected.Thus, more satellite and ground nodes can obtain edge services, which effectively reduces the average transmission delay of the system.In the experimental part, a simulation platform based on Matlab and STK is established.The simulation results show that the proposed algorithm can effectively reduce the average transmission delay of traditional satellite network, and the optimization effect is also greatly improved compared with particle swarm optimization algorithm and cluster deployment algorithm.

关 键 词：天地一体化智能网络 移动边缘计算 网络分簇算法 人工蜂群算法 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]