一种基于AAE的协同多播主动缓存方案  

Collaborative Multicast Proactive Caching Scheme Based on AAE

作　　者：刘鑫[1] 王珺[1] 宋巧凤 刘家豪 LIU Xin;WANG Jun;SONG Qiao-feng;LIU Jia-hao(School of Communication and Information Engineering,Nanjing University of Posts and Telecommunications,Nanjing 210003,China)

机构地区：[1]南京邮电大学通信与信息工程学院,南京210003

出　　处：《计算机科学》2022年第9期260-267,共8页Computer Science

摘　　要：随着用户终端数量的激增和5G技术的发展,形成了宏基站和小基站并存的网络。同时超高清视频、云VR/AR等应用对时延提出了更高的要求。为了缩短5G网络中的时延,文中结合小基站协同、多播和用户行为可预测的特性,提出了一种基于对抗自动编码(Adversarial Autoencoders, AAE)的协同多播主动缓存方案(Collaborative Multicast Proactive Caching Scheme Based on Adversarial Autoencoders, CMPCAAE)。该方案首先根据用户的特征信息将用户划分成偏好不同的用户组,然后通过AAE预测每个用户组可能请求的内容。为了减少缓存内容的冗余,采用蚁群算法(Ant Colony, ACO)将预测的内容预先部署到各小基站以实现小基站间的协同。在内容分发阶段,若分组中用户请求的是流行度高的内容,则以多播的方式将该内容主动缓存到分组中其他未发送请求的用户,否则以正常的方式进行分发。仿真结果表明,CMPCAAE方案在系统的平均请求时延和丢失率方面均优于经典的缓存方案。With the increasing number of user terminals and the development of 5 G technology, a network has been formed where macro base stations and small base stations co-exist.Meanwhile, applications such as ultra-high resolution video and cloud VR/AR have higher requirements for latency.In order to reduce the latency in 5 G networks, a cooperative multicast proactive caching scheme based on adversarial automatic coding is proposed in this paper.In this scheme, firstly, users are divided into different groups based on their characteristics.And then the content that the group may request will be predicated by using AAE.To reduce the redundancy of cached contents, the ant colony algorithm is used to pre-deploy the predicted contents to each small base station.Finally, in the content distribution phase, if a user requests a content with high popularity, the content will be proactively cached in a multicast manner to other users in this group who don’t send the request, otherwise it is distributed in a normal manner.Simulation results show that the CMPCAAE scheme outperforms the classical caching scheme in terms of average delay and missing ratio of the system.

关 键 词：边缘缓存 协同缓存 主动缓存 对抗自动编码 多播 蚁群算法 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]