Learning From Images: Proactive Caching With Parallel Convolutional Neural Networks

作     者：Wang, Yantong Hu, Ye Yang, Zhaohui Saad, Walid Wong, Kai-Kit Friderikos, Vasilis 

作者机构：Shandong Normal Univ Sch Informat Sci & Engn Jinan 250358 Peoples R China Columbia Univ Dept Elect Engn New York NY 24061 USA Zhejiang Univ Coll Informat Sci & Elect Engn Hangzhou 310027 Peoples R China Virginia Tech Bradley Dept Elect & Comp Engn WirelessVT Arlington VA 22203 USA UCL Dept Elect & Elect Engn London WC1E 6BT England Kings Coll London Ctr Telecommun Res Dept Engn London WC2R 2LS England 

出 版 物：《IEEE TRANSACTIONS ON MOBILE COMPUTING》 (IEEE Trans. Mob. Comput.)

年 卷 期：2023年第22卷第12期

页      面：7234-7248页

核心收录：

学科分类：0810[工学-信息与通信工程] 0808[工学-电气工程] 08[工学] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

主　　题：Costs Convolutional neural networks Training Optimization Gray-scale Prediction algorithms Base stations grayscale image mixed integer linear programming proactive caching 

摘      要：With the continuous trend of data explosion, delivering packets from data servers to end users causes increased stress on both the fronthaul and backhaul traffic of mobile networks. To mitigate this problem, caching popular content closer to the end-users has emerged as an effective method for reducing network congestion and improving user experience. To find the optimal locations for content caching, many conventional approaches construct various Mixed Integer Linear Programming (MILP) models. However, such methods may fail to support online decision making due to the inherent curse of dimensionality. In this paper, a novel framework for proactive caching is proposed. This framework merges model-based optimization with data-driven techniques by transforming an optimization problem into a grayscale image. For parallel training and simple design purposes, the proposed MILP model is first decomposed into a number of sub-problems and, then, Convolutional Neural Networks (CNNs) are trained to predict content caching locations of these sub-problems. Furthermore, since the MILP model decomposition neglects the network resources (such as caching space and link bandwidth) competition among sub-problems, the CNNs outputs have the risk to be infeasible solutions. Therefore, two algorithms are provided: the first uses predictions from CNNs as an extra constraint to reduce the number of decision variables;the second employs CNNs outputs to accelerate local search. Numerical results show that the proposed scheme can reduce 71.6% computation time, whose computation time reaches around 28.9ms, with only 0.8% additional performance cost compared to the MILP solution, which provides high quality decision making in pseudo real-time.