quotation:[Copy]
[Copy]
【Print page】 【Download 【PDF Full text】 View/Add CommentDownload reader Close

←Previous page|Page Next →

Back Issue    Advanced search

This Paper:Browse 1875   Download 0  
基于自动导引车时-空信息使能的边云服务迁移策略
于存谦,李靖宇,李航,张春芳,何荣希,林彬
0
(1.大连海事大学 信息科学技术学院,辽宁 大连 116026;2.沈阳航空航天大学 计算机学院,沈阳 110136;3.鹏程实验室 网络通信研究中心,广东 深圳 518052)
摘要:
分析了利用Container解决自动导引车(Automatic Guided Vehicle,AGV)移动而导致的资源和延迟失配问题的可行性,采用了C-RAN(Cloud-Radio Access Network)、吉比特无源光网络、光城域网和云数据中心在内的融合网络架构。通过AGV在小区的停留时间以及AGV移动后所处的空间位置,设计了同时最小化服务时延和迁移开销的双目标动态容器迁移(Dynamic Container Migration,DCM)优化框架,最后提出了基于AGV时域和空间位置信息的自适应Container迁移算法(Adaptive Container Migration Algorithm based on Time-domain and Location Information,ACMA-TLI)。仿真结果验证了所提算法在迁移时延、迁移开销和资源均衡等方面的优势,且与对比算法相比在平均延迟方面的提升可达124 s。
关键词:  边缘-云网络  服务迁移  路由与频谱分配  自动导引车  动态容器迁移
DOI:
基金项目:国家自然科学基金资助项目(61971083,61801074,61371091,51939001);中国博士后科学面上基金(2019M661074);辽宁省自然科学基金(2019-BS-021);大连市科技创新基金重点学科重大课题(2019J11CY015)
Edge-cloud service migration strategy based on enabled temporal-geographic information of automatic guided vehicle
YU Cunqian,LI Jingyu,LI Hang,ZHANG Chunfang,HE Rongxi,LIN Bin
(1.Institute of Information Science Technology,Dalian Maritime University,Dalian 116026,China;2.School of Computer Science,Shenyang Aerospace University,Shenyang 110136,China; 3.Network Communication Research Centre,Peng Cheng Laboratory,Shenzhen 518052,China)
Abstract:
This paper discusses the feasibility of adopting container to solve the resource and delay mismatch caused by the rapid movement of automatic guided vehicle(AGV),and then introduces both the network architecture composed of cloud-radio access network(C-RAN),gigabit passive optical network and optical core networks and cloud data center.Besides,according to the AGVs stay time in the cell and the spatial location of the AGV after moving,a dual-objective dynamic container migration(DCM) optimization is proposed to minimize both the service delay and migration cost.An adaptive container migration algorithm based on time-domain and location information(ACMA-TLI) is proposed.The simulation results verify the advantages of the proposed algorithm in terms of migration delay,cost and resource balance,and compared with that of the benchmarks,the improvement in average delay can reach 124 s.
Key words:  edge-cloud network  service migration  routing and spectrum allocation  automatic guided vehicle  dynamic container migration