Combining graph neural network with deep reinforcement learning for resource allocation in computing force networks

被引:1
|
作者
Han, Xueying [1 ]
Xie, Mingxi [2 ]
Yu, Ke [2 ]
Huang, Xiaohong [1 ]
Du, Zongpeng [3 ]
Yao, Huijuan [3 ]
机构
[1] Beijing Univ Posts & Telecommun, Sch Comp Sci, Beijing 100876, Peoples R China
[2] Beijing Univ Posts & Telecommun, Sch Artificial Intelligence, Beijing 100876, Peoples R China
[3] China Mobile Res Inst, Dept Infrastructure Network Technol Res, Beijing 100032, Peoples R China
关键词
Computing force network; Routing optimization; Deep learning; Graph neural network; Resource allocation; CLOUD; MANAGEMENT;
D O I
10.1631/FITEE.2300009
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
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.
引用
收藏
页码:701 / 712
页数:12
相关论文
共 50 条
  • [1] Deep Reinforcement Learning and Graph Neural Networks for Efficient Resource Allocation in 5G Networks
    Randall, Martin
    Belzarena, Pablo
    Larroca, Federico
    Casas, Pedro
    [J]. 2022 IEEE LATIN-AMERICAN CONFERENCE ON COMMUNICATIONS (LATINCOM), 2022,
  • [2] Deep Reinforcement Learning for Offloading and Resource Allocation in Vehicle Edge Computing and Networks
    Liu, Yi
    Yu, Huimin
    Xie, Shengli
    Zhang, Yan
    [J]. IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY, 2019, 68 (11) : 11158 - 11168
  • [3] Combining Deep Reinforcement Learning With Graph Neural Networks for Optimal VNF Placement
    Sun, Penghao
    Lan, Julong
    Li, Junfei
    Guo, Zehua
    Hu, Yuxiang
    [J]. IEEE COMMUNICATIONS LETTERS, 2021, 25 (01) : 176 - 180
  • [4] An autonomous architecture based on reinforcement deep neural network for resource allocation in cloud computing
    Javaheri, Seyed Danial Alizadeh
    Ghaemi, Reza
    Naeen, Hossein Monshizadeh
    [J]. COMPUTING, 2024, 106 (02) : 371 - 403
  • [5] An autonomous architecture based on reinforcement deep neural network for resource allocation in cloud computing
    Seyed Danial Alizadeh Javaheri
    Reza Ghaemi
    Hossein Monshizadeh Naeen
    [J]. Computing, 2024, 106 : 371 - 403
  • [6] Deep Reinforcement Learning for Communication and Computing Resource Allocation in RIS Aided MEC Networks
    Xi, Jianpeng
    Ai, Bo
    Chen, Liangyu
    Wu, Lina
    [J]. IEEE INTERNATIONAL CONFERENCE ON COMMUNICATIONS (ICC 2022), 2022, : 3184 - 3189
  • [7] Deep reinforcement learning guided graph neural networks for brain network analysis
    Zhao, Xusheng
    Wu, Jia
    Peng, Hao
    Beheshti, Amin
    Monaghan, Jessica J. M.
    McAlpine, David
    Hernandez-Perez, Heivet
    Dras, Mark
    Dai, Qiong
    Li, Yangyang
    Yu, Philip S.
    He, Lifang
    [J]. NEURAL NETWORKS, 2022, 154 : 56 - 67
  • [8] Offloading and Resource Allocation With General Task Graph in Mobile Edge Computing: A Deep Reinforcement Learning Approach
    Yan, Jia
    Bi, Suzhi
    Zhang, Ying-Jun Angela
    [J]. IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS, 2020, 19 (08) : 5404 - 5419
  • [9] Deep Reinforcement Learning for Edge Computing Resource Allocation in Blockchain Network Slicing Broker Framework
    Gong, Yu
    Sun, Siyuan
    Wei, Yifei
    Song, Mei
    [J]. 2021 IEEE 93RD VEHICULAR TECHNOLOGY CONFERENCE (VTC2021-SPRING), 2021,
  • [10] Resource Allocation in Vehicular Communications using Graph and Deep Reinforcement Learning
    Gyawali, Sohan
    Qian, Yi
    Hu, Rose Qingyang
    [J]. 2019 IEEE GLOBAL COMMUNICATIONS CONFERENCE (GLOBECOM), 2019,