基于图协同过滤模型的D2D协作缓存策略

D2D cooperative caching strategy based on graph collaborative filtering model

针对设备到设备(D2D)缓存中基站信号覆盖范围有限导致的难以获得足够数据来预测用户偏好的问题,提出了一种基于图协同过滤模型的D2D协作缓存策略。首先,构建图协同过滤模型,通过多层图卷积神经网络捕捉用户-内容交互图中的高阶连通信息,并利用多层感知机学习用户和内容之间的非线性关系来预测用户偏好。其次,为了最小化平均访问时延,综合考虑用户偏好和缓存时延收益,将缓存内容放置问题建模为马尔可夫决策过程模型,设计基于深度强化学习的协作缓存算法进行求解。仿真实验表明,与现有的缓存策略相比,所提缓存策略在不同的内容种类、用户密度和D2D通信距离参数下均取得了最优的性能效果。

A D2D cooperative caching strategy based on graph collaborative filtering model was proposed for the problem of difficulty in obtaining sufficient data to predict user preferences in device-to-device(D2D)caching due to the limited signal coverage of base stations.Firstly,a graph collaborative filtering model was constructed,which captured the higher-order connectivity information in the user-content interaction graph through a multilayer graph convolutional neural network,and a multilayer perceptron was used to learn the nonlinear relationship between users and content to predict user preferences.Secondly,in order to minimize the average access delay,considering user preference and cache delay benefit,the cache content placement problem was modeled as a Markov decision process model,and a cooperative cache algorithm based on deep reinforcement learning was designed to solve it.Simulation experiments show that the proposed caching strategy achieves optimal performance compared with existing caching strategies for different content types,user densities,and D2D communication distance parameters.