计算机应用研究2025，Vol.42Issue(10)：3114-3121,8.DOI:10.19734/j.issn.1001-3695.2025.03.0079
移动边缘网络的内容缓存和推荐联合决策方案
Joint content caching and recommendation decision-making scheme in mobile edge network
摘要
Abstract
Content caching at the mobile edge network is an effective way of mitigating backhaul load and improving user ex-perience.The recent studies have found that the combination of caching and recommendation can improve the efficiency of edge caching and reduce the transmission delay.Under the collaborative edge caching network model with recommendation support,the problem of edge caching and content recommendation is modeled as a multi-agent multi-armed bandit problem.Firstly,the paper used GCN model to predict user preferences and obtain content popularity.Secondly,with defining the recommended exploration window based on user tolerance rate for content recommendation,the paper designed the strategy of exploration and utilization and the strategy of income renewal,and proposed a multi-armed bandit based caching and recom-mendation algorithm MAMAB-JCR to implement caching and recommendation joint decisions.Finally,the paper compared the proposed MAMAB-JCR algorithm with three baseline algorithms(DDQN,JCCR and MAMAB-C)in experiments.Experimental results show that the proposed algorithm can reduce delay of content transmission,enhance cache hit ratio and improve user ex-perience.关键词
移动边缘网络/协同缓存/内容推荐/多臂轮赌/强化学习Key words
mobile edge network(MEC)/cooperative caching/content recommendation/multi-armed bandit/reinforcement learning分类
计算机与自动化引用本文复制引用
周继鹏,唐飘..移动边缘网络的内容缓存和推荐联合决策方案[J].计算机应用研究,2025,42(10):3114-3121,8.基金项目
国家自然科学基金资助项目(62272198,62172189) （62272198,62172189）
