一种空间信息网络缓存决策策略  

Cache decision strategy for space information network

作　　者：蔡睿妍 钱杨 魏德宾 Cai Ruiyan;Qian Yang;Wei Debin(School of Electronics&Information Engineering,Taizhou University,Taizhou Zhejiang 318000,China;Communication&Network Key Laboratory,Dalian University,Dalian Liaoning 116622,China;College of Information&Engineering,Dalian University,Dalian Liaoning 116622,China)

机构地区：[1]台州学院电子与信息工程学院,浙江台州318000 [2]大连大学通信与网络重点实验室,辽宁大连116622 [3]大连大学信息工程学院,辽宁大连116622

出　　处：《计算机应用研究》2022年第12期3750-3754,共5页Application Research of Computers

基　　金：国家自然基金青年基金资助项目(61901080)。

摘　　要：针对空间信息网络(space information network,SIN)中卫星节点缓存容量有限,且卫星高速移动使得星间链路时变,导致地面用户内容访问延迟增大的问题,提出一种基于人工蜂群算法的空间信息网络缓存决策策略(satellite improved artificial bee colony,SIABC)。首先根据低轨卫星节点链路切换的周期性和可预知性,建立网络分区模型,对空间信息网络的卫星节点进行分区,在此基础上,建立区域节点协作缓存模型,使得整个网络区域内的卫星节点有选择性地缓存不同流行度的内容,同时兼顾区域内节点的协作缓存,从而流行度高的内容缓存在网络边缘。仿真结果表明,与现有缓存机制相比,该缓存策略能够明显提高内容的平均缓存命中率,并显著降低用户的内容访问时延。Aiming at the limited cache capacity of satellite nodes in the SIN,and the high-speed movement of satellites makes the inter-satellite link time-varying,which leads to an increase in the delay of terrestrial user content access,this paper proposed a decision-making strategy for spatial information network caching based on artificial bee colony algorithm(SIABC).Firstly,according to the periodicity and predictability of link switching of low-orbit satellite nodes,it established a network partition model,and partitioned the satellite nodes of the SIN.On this basis,it established a regional node cooperative cache model,which made the satellite nodes in the entire network area selectively cache content of different popularity,and also took taking into account the cooperative caching of nodes in the area,so that cached the content with high popularity at the edge of the network.The simulation results show that,compared with the existing caching mechanism,the caching strategy can significantly improve the average cache hit rate of the content and significantly reduce the content access delay of users.

关 键 词：低轨卫星 网络分区 缓存 人工蜂群算法 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]