图神经网络与深度强化学习结合的算力网络资源分配方法
Combining graph neural network with deep reinforcement learning for resource allocation in computing force networks
韩雪莹 1谢明熹 2禹可 2黄小红 1杜宗鹏 3姚惠娟3
作者信息
- 1. 北京邮电大学计算机学院(国家示范性软件学院),中国 北京市,100876
- 2. 北京邮电大学人工智能学院,中国 北京市,100876
- 3. 中国移动研究院基础网络技术研究所,中国 北京市,100032
- 折叠
摘要
由于具有特定计算需求及超低延迟传输需求的实时应用呈现爆炸性增长,算力网络成为热门研究课题.当前算力网络的主要挑战是如何权衡网络资源与计算资源,作出联合最优决策.尽管近年来深度强化学习在网络优化方面取得一定进步,但这些方法仍然受到拓扑结构变化的影响,特别是对未在训练中出现的网络拓扑作出决策.本文提出一个基于图神经网络的深度强化学习框架,使得智能体在进行网络与计算资源联合优化的同时,兼具拓扑泛化性,更加适应网络拓扑的动态变化.借助图神经网络的泛化优势,该方法可在变动的网络拓扑中运行,且相比基于传统深度强化学习的方法具有更强的优化决策能力.
Abstract
Fueled by the explosive growth of ultra-low-latency and real-time applications with specific computing and network performance requirements,the computing force network(CFN)has become a hot research subject.The primary CFN challenge is to leverage network resources and computing resources.Although recent advances in deep reinforcement learning(DRL)have brought significant improvement in network optimization,these methods still suffer from topology changes and fail to generalize for those topologies not seen in training.This paper proposes a graph neural network(GNN)based DRL framework to accommodate network traffic and computing resources jointly and efficiently.By taking advantage of the generalization capability in GNN,the proposed method can operate over variable topologies and obtain higher performance than the other DRL methods.
关键词
算力网络/路由优化/深度学习/图神经网络/资源分配Key words
Computing force network/Routing optimization/Deep learning/Graph neural network/Resource allocation引用本文复制引用
基金项目
Beijing University of Posts and Telecommunications-China Mobile Research Institute Joint Innovation Center()
出版年
2024
NETL
NSTL
万方数据