一种用户聚集场景下的层级计算卸载策略  

A HIERARCHICAL COMPUTING OFFLOADING STRATEGY FOR USER AGGREGATION SCENARIOS

作　　者：陶聪 张红梅[1] 张向利[1] 钟楠 Tao Cong;Zhang Hongmei;Zhang Xiangli;Zhong Nan(Key Laboratory of Cognitive Radio and Information Processing,Ministry of Education,Guilin University of Electronic Technology,Guilin 541004,Guangxi,China)

机构地区：[1]桂林电子科技大学认知无线电与信息处理教育部重点实验室,广西桂林541004

出　　处：《计算机应用与软件》2024年第8期108-115,148,共9页Computer Applications and Software

基　　金：认知无线电与信息处理教育部重点实验室基金项目(CRKL200101);广西无线宽带通信与信号处理重点实验室2020年主任基金项目(GXKL06200104);广西自然科学基金重点项目(2020GXNSFDA238001)。

摘　　要：现有的边缘计算研究集中于无线资源分配和计算资源分配,而对用户聚集场景下的边缘协同问题研究较少。针对此问题提出一种用户聚集场景下的层级计算卸载策略。该策略采用FSA-MCS解决多重基站信号覆盖下的用户终端卸载节点选择问题;设计一种层级结构的启发式区域计算卸载算法,能够有效提高用户聚集场景下限定时间内完成的任务数量,并减少了用户卸载总时延。实验结果表明,与其他卸载方法相比,该策略的用户任务在限定时间内成功计算完成率最高提高32.7百分点,卸载总时延最高减少43.3%。Existing edge computing researches focus on wireless resource allocation and computational resource allocation.However,the research on cooperative computing in user aggregation scenarios is ignored.Aiming at this problem,this paper proposes a hierarchical computation offloading strategy for user aggregation scenarios.The strategy adopted FSA-MCS to solve the problem of offloading node selection for user terminals under multiple base station signal coverage,and designed a heuristic regional computational offloading algorithm with a hierarchical structure,which was able to effectively increase the number of tasks completed within a limited time under user aggregation scenarios and reduce the total user offloading delay.The experimental results show that compared with other offloading methods,this strategy increases the successful computation completion rate of user tasks within the limited time by up to 32.7 percentage points and reduces the total offloading delay by up to 43.3%.

关 键 词：边缘计算 计算卸载 资源分配 协同计算 层级调度 

分 类 号：TP3[自动化与计算机技术—计算机科学与技术]