Reinforcement Learning-based Multi-domain Network Slice Provisioning

被引:0
作者
Wu, Zhouxiang [1 ]
Ishigaki, Genya [2 ]
Gour, Riti [3 ]
Li, Congzhou [1 ]
Mi, Feng [1 ]
Talluri, Subhash [4 ]
Jue, Jason P. [1 ]
机构
[1] Univ Texas Dallas, Dept Comp Sci, Richardson, TX 75080 USA
[2] San Jose State Univ, Dept Comp Sci, San Jose, CA 95192 USA
[3] Cent Connecticut State Univ, Dept Comp Elect & Graph Technol, New Britain, CT 06050 USA
[4] Amazon Web Serv, Seattle, WA 98108 USA
来源
ICC 2023-IEEE INTERNATIONAL CONFERENCE ON COMMUNICATIONS | 2023年
基金
美国国家科学基金会;
关键词
Network Slice; Resource Allocation; Machine Learning; Reinforcement Learning; Graph Neural Network;
D O I
10.1109/ICC45041.2023.10278745
中图分类号
TN [电子技术、通信技术];
学科分类号
0809 ;
摘要
We address the problem of establishing an end-to-end network slice across multiple domains and propose a Reinforcement Learning-based framework that enables multiple domains to collaborate on end-to-end network slicing admission and allocation. The objective is to maximize the long-term revenue of the network operator. We employ a Graph Neural Network (GNN) to capture the topology features as the encoder. The simulation results show that our framework improves the profit of the network operator by up to 15% compared to a greedy algorithm.
引用
收藏
页码:1899 / 1904
页数:6
相关论文
共 8 条
[1]   AN EXISTENCE THEOREM FOR DISCRETE-TIME INFINITE-HORIZON OPTIMAL-CONTROL PROBLEMS [J].
KEERTHI, SS ;
GILBERT, EG .
IEEE TRANSACTIONS ON AUTOMATIC CONTROL, 1985, 30 (09) :907-909
[2]   Deep Reinforcement Learning for Resource Management in Network Slicing [J].
Li, Rongpeng ;
Zhao, Zhifeng ;
Sun, Qi ;
I, Chih-Lin ;
Yang, Chenyang ;
Chen, Xianfu ;
Zhao, Minjian ;
Zhang, Honggang .
IEEE ACCESS, 2018, 6 :74429-74441
[3]   Neural Network for Graphs: A Contextual Constructive Approach [J].
Micheli, Alessio .
IEEE TRANSACTIONS ON NEURAL NETWORKS, 2009, 20 (03) :498-511
[4]   FROM NETWORK SHARING TO MULTI-TENANCY: THE 5G NETWORK SLICE BROKER [J].
Samdanis, Konstantinos ;
Costa-Perez, Xavier ;
Sciancalepore, Vincenzo .
IEEE COMMUNICATIONS MAGAZINE, 2016, 54 :32-39
[5]   RL-NSB: Reinforcement Learning-Based 5G Network Slice Broker [J].
Sciancalepore, Vincenzo ;
Costa-Perez, Xavier ;
Banchs, Albert .
IEEE-ACM TRANSACTIONS ON NETWORKING, 2019, 27 (04) :1543-1557
[6]   On Multi-Domain Network Slicing Orchestration Architecture and Federated Resource Control [J].
Taleb, Tarik ;
Afolabi, Ibrahim ;
Samdanis, Konstantinos ;
Yousaf, Faqir Zarrar .
IEEE NETWORK, 2019, 33 (05) :242-252
[7]   A Reinforcement Learning-Based Routing Strategy for Elastic Network Slices [J].
Wu, Zhouxiang ;
Jue, Jason P. .
IEEE INTERNATIONAL CONFERENCE ON COMMUNICATIONS (ICC 2022), 2022, :5505-5510
[8]   A Reinforcement Learning-Based Admission Control Strategy for Elastic Network Slices [J].
Wu, Zhouxiang ;
Ishigaki, Genya ;
Gour, Riti ;
Jue, Jason P. .
2021 IEEE GLOBAL COMMUNICATIONS CONFERENCE (GLOBECOM), 2021,