基于图强化学习的多边缘协同负载均衡方法  

Graph Reinforcement Learning Based Multi-edge Cooperative Load Balancing Method

作　　者：郑龙海 肖博怀 姚泽玮 陈星[1,2,3] 莫毓昌[4] ZHENG Longhai;XIAO Bohuai;YAO Zewei;CHEN Xing;MO Yuchang(College of Computer and Data Science,Fuzhou University,Fuzhou 350116,China;Engineering Research Center of Big Data Intelligence,Ministry of Education,Fuzhou 350002,China;Fujian Key Laboratory of Network Computing and Intelligent Information Processing,Fuzhou University,Fuzhou 350116,China;Fujian Province University Key Laboratory of Computational Science,Huaqiao University,Quanzhou,Fujian 362021,China)

机构地区：[1]福州大学计算机与大数据学院,福州350116 [2]大数据智能教育部工程研究中心,福州350002 [3]福建省网络计算与智能信息处理重点实验室,福州350116 [4]华侨大学计算科学福建省高校重点实验室,福建泉州362021

出　　处：《计算机科学》2025年第3期338-348,共11页Computer Science

基　　金：国家自然科学基金(62072108);福建省科技经济融合服务平台(2023XRH001);福厦泉国家自主创新示范区协同创新平台项目(2022FX5)。

摘　　要：在移动边缘计算中,设备通过将计算密集型任务卸载到附近边缘服务器,可以有效减少应用程序的延迟和能耗。为了提高服务质量,边缘服务器之间需要协作而非单独工作。针对多边缘协作的负载均衡问题,现有的策略往往依赖于精确的数学模型或缺乏对边缘拓扑关系的利用。为了解决此问题,文中提出了一种基于图强化学习的卸载决策方法。首先将多边缘协作的负载均衡场景抽象为图数据;然后采用基于图卷积神经网络的图嵌入过程来提取图的信息特征,以辅助深度Q网络进行卸载决策;最后通过集中反馈控制机制找到目标负载均衡方案。在多个场景下进行仿真实验,实验结果验证了所提方法在缩短任务平均响应时延方面的有效性,并且可以在短时间内获得优于对比算法且接近理想方案的负载均衡效果。In mobile edge computing,devices can effectively relieve latency and energy consumption by offloading computation-intensive tasks to nearby edge servers.In order to improve the quality of service,edge servers need to collaborate with each other rather than working alone.For the load balancing problem of multi-edge collaboration,the existing solutions often depend on accurate mathematical models or make fair use of edge topological relationships.To solve this problem,an offloading decision-ma-king method based on graph reinforcement learning is proposed in this paper.Firstly,the load balancing scenario with multi-edge collaboration is abstracted as graph data,then a graph embedding process based on graph convolutional neural network is used to extract the information features of the graph,for assisting the deep Q-network to make offloading decisions,and finally the objective load balancing plan is found through a centralized feedback-control mechanism.Simulation experiments are conducted in multiple scenarios,the results verify the effectiveness of the proposed method in shortening the average response latency of the tasks,and the load balancing effect which is better than the comparison algorithms and close to the ideal plan can be obtained in a short period of time.

关 键 词：多边缘协作 负载均衡 任务卸载 图神经网络 深度强化学习 

分 类 号：TP338[自动化与计算机技术—计算机系统结构]