On Cost Minimization for Cache-Enabled D2D Networks with Recommendation

作     者：Yu Hua Yaru Fu Qi Zhu Yu Hua;Yaru Fu;Qi Zhu

作者机构：The Key Wireless Laboratory of Jiangsu ProvinceNanjing University of Posts and TelecommunicationsNanjing 210003China School of Science and TechnologyHong Kong Metropolitan UniversityHong Kong 999077China 

出 版 物：《China Communications》 (中国通信（英文版）)

年 卷 期：2022年第19卷第11期

页      面：257-267页

核心收录：

学科分类：0810[工学-信息与通信工程] 08[工学] 0804[工学-仪器科学与技术] 080402[工学-测试计量技术及仪器] 

基　　金：supported in part by the grant from the Research Grants Council of the Hong Kong Special Administrative Region,China(Project Reference No.UGC/FDS16/E09/21) in part by the Hong Kong President’s Advisory Committee on Research and Development(PACRD)under Project No.2020/1.6,in part by the National Natural Science Foundation of China(NSFC)under Grants No.61971239 and No.92067201 in part by Jiangsu Provincial Key Research and Development Program under grant No.BE2020084-4 in part by Postgraduate Research&Practice Innovation Program of Jiangsu Province under Grant KYCX200714. 

主　　题：edge caching cost minimization D2D communication recommendation systems 

摘      要：To accommodate the tremendous increase of mobile data traffic,cache-enabled device-to-device(D2D)communication has been taken as a promising technique to release the heavy burden of cellular networks since popular contents can be pre-fetched at user devices and shared among subscribers.As a result,cellular traffic can be offloaded and an enhanced system performance can be attainable.However,due to the limited cache capacity of mobile devices and the heterogeneous preferences among different users,the requested contents are most likely not be proactively cached,inducing lower cache hit ratio.Recommendation system,on the other hand,is able to reshape users’request schema,mitigating the heterogeneity to some extent,and hence it can boost the gain of edge caching.In this paper,the cost minimization problem for the social-aware cache-enabled D2D networks with recommendation consideration is investigated,taking into account the constraints on the cache capacity budget and the total number of recommended files per user,in which the contents are sharing between the users that trust each other.The minimization problem is an integer non-convex and non-linear programming,which is in general NP-hard.Therewith,we propose a timeefficient joint recommendation and caching decision scheme.Extensive simulation results show that the proposed scheme converges quickly and significantly reduces the average cost when compared with various benchmark strategies.