摘要
针对移动虚拟现实(VR)视频在传统传输架构下分发时延过大问题,提出一种基于多MEC协作缓存和传输的网络架构。首先,考虑到移动VR视频在观看时需要计算处理而移动VR设备并不一定具备相应的处理能力,提出让传输架构中的MEC来承担这部分计算任务。然后,建立以最小化平均分发时延为优化目标的混合整数线性规划缓存模型,通过商业求解器Gurobi来获得移动VR视频的最佳缓存位置。最后,通过数值仿真实验证明,与传统的缓存算法相比较,提出的缓存和传输策略能有效降低移动VR视频的平均分发时延。
In this paper,a network architecture based on multi-MEC(mobile edge computing)cooperative caching and streaming is proposed to address the problem that the delivery latency of mobile virtual reality(VR)video is too high under traditional delivery architecture.First of all,considering that the mobile VR video needs computing processing when watching and the mobile VR device may not always have the corresponding processing capacity,the MEC in the transmission architecture undertakes the needed computing task.Then,a mixed-integer linear programming(MILP)cache model with the optimization goal of minimizing the average delivery latency is established,and the optimal cache placement for mobile VR videos is obtained through the commercial solver Gurobi.Finally,numerical simulation experiments show that the proposed caching and streaming strategy can effectively reduce the average delivery latency of mobile VR videos when compared with existing caching algorithms.
作者
郑成渝
夏靖雯
陈路遥
唐勇
杨挺
刘强
ZHENG Chengyu;XIA Jingwen;CHEN Luyao;TANG Yong;YANG Ting;LIU Qiang(China Telecom Sichuan Branch,Chengdu 610000;School of Computer Science and Engineering,University of Electronic Science and Technology of China,Chengdu 611731;Faculty of Innovation Engineering,Macao University of Science and Technology,Macao China 999078)
出处
《电子科技大学学报》
EI
CAS
CSCD
北大核心
2023年第5期765-772,共8页
Journal of University of Electronic Science and Technology of China
基金
四川省科技厅项目(2021YFHO171)。
