A Fault-Tolerant Mobility-Aware Caching Method in Edge Computing  

作　　者：Yong Ma Han Zhao Kunyin Guo Yunni Xia Xu Wang Xianhua Niu Dongge Zhu Yumin Dong 

机构地区：[1]School of Computer Information Engineering,Jiangxi Normal University,Nanchang,330000,China [2]School of Digital Industry,Jiangxi Normal University,Shangrao,334000,China [3]The College of Computer Science,Chongqing University,Chongqing,400044,China [4]College of Mechanical and Vehicle Engineering,Chongqing University,Chongqing,400030,China [5]School of Computer and Software Engineering,Xihua University,Chengdu,610039,China [6]Electric Power Research Institute of State Grid Ningxia Electric Power Company Ltd.,Yinchuan,750002,China [7]College of Computer and Information Science,Chongqing Normal University,Chongqing,401331,China

出　　处：《Computer Modeling in Engineering & Sciences》2024年第7期907-927,共21页工程与科学中的计算机建模（英文）

基　　金：supported by the Innovation Fund Project of Jiangxi Normal University(YJS2022065);the Domestic Visiting Program of Jiangxi Normal University.

摘　　要：Mobile Edge Computing(MEC)is a technology designed for the on-demand provisioning of computing and storage services,strategically positioned close to users.In the MEC environment,frequently accessed content can be deployed and cached on edge servers to optimize the efficiency of content delivery,ultimately enhancing the quality of the user experience.However,due to the typical placement of edge devices and nodes at the network’s periphery,these components may face various potential fault tolerance challenges,including network instability,device failures,and resource constraints.Considering the dynamic nature ofMEC,making high-quality content caching decisions for real-time mobile applications,especially those sensitive to latency,by effectively utilizing mobility information,continues to be a significant challenge.In response to this challenge,this paper introduces FT-MAACC,a mobility-aware caching solution grounded in multi-agent deep reinforcement learning and equipped with fault tolerance mechanisms.This approach comprehensively integrates content adaptivity algorithms to evaluate the priority of highly user-adaptive cached content.Furthermore,it relies on collaborative caching strategies based onmulti-agent deep reinforcement learningmodels and establishes a fault-tolerancemodel to ensure the system’s reliability,availability,and persistence.Empirical results unequivocally demonstrate that FTMAACC outperforms its peer methods in cache hit rates and transmission latency.

关 键 词：Mobile edge networks MOBILITY fault tolerance cooperative caching multi-agent deep reinforcement learning content prediction 

分 类 号：TP311[自动化与计算机技术—计算机软件与理论]