Federated Multiagent Deep Reinforcement Learning for Intelligent IoT Wireless Communications: Overview and Challenges

被引：0

作者：

De Oliveira, Hugo ^{[1
,2
]}

Kaneko, Megumi ^{[3
]}

Boukhatem, Lila ^{[4
]}

机构：

[1] Paris Saclay Univ, Dual Degree Program, F-91190 Gif Sur Yvette, France

[2] Grad Univ Adv Studies SOKENDAI, Tokyo 1018430, Japan

[3] Natl Inst Informat, Tokyo 1018430, Japan

[4] Interdisciplinary Lab Numer Sci LISN, F-91190 Gif Sur Yvette, France

来源：

IEEE VEHICULAR TECHNOLOGY MAGAZINE | 2024年 / 19卷 / 04期

关键词：

Privacy; Wireless communication; Training; Performance evaluation; Industrial Internet of Things; Delays; Data privacy;

D O I：

10.1109/MVT.2024.3451191

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

The soaring number of connected Internet of Things (IoT) devices and their extreme quality of service (QoS) demands in terms of rate, delay, and reliability pose multiple issues for beyond-5G (B5G) and 6G systems. As devices, applications, and mobile interfaces become increasingly diverse, optimizing the utilization of the scarce spectrum will be ever more challenging. Mathematical optimization techniques alone appear insufficient to provide viable solutions for such complex networks in real time.

引用

页码：73 / 82

页数：10

共 15 条

[1] Decentralized Aggregation for Energy-Efficient Federated Learning via D2D Communications [J].

Al-Abiad, Mohammed S. ;

Obeed, Mohanad ;

Hossain, Md. Jahangir ;

Chaaban, Anas .

IEEE TRANSACTIONS ON COMMUNICATIONS, 2023, 71 (06) :3333-3351

[2]

Arivazhagan M. G., 2019, ARXIV

[3] Federated Multi-Agent Deep Reinforcement Learning (Fed-MADRL) for Dynamic Spectrum Access [J].

Chang, Hao-Hsuan ;

Song, Yifei ;

Doan, Thinh T. ;

Liu, Lingjia .

IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS, 2023, 22 (08) :5337-5348

[4] Deep Reinforcement Learning-Aided Optimization of Multi-Interface Allocation for Short-Packet Communications [J].

De Oliveira, Hugo ;

Kaneko, Megumi ;

Boukhatem, Lila ;

Fukuda, Ellen Hidemi .

IEEE TRANSACTIONS ON COGNITIVE COMMUNICATIONS AND NETWORKING, 2023, 9 (03) :738-753

[5] Single and Multi-Agent Deep Reinforcement Learning for AI-Enabled Wireless Networks: A Tutorial [J].

Feriani, Amal ;

Hossain, Ekram .

IEEE COMMUNICATIONS SURVEYS AND TUTORIALS, 2021, 23 (02) :1226-1252

[6] Federated Learning: A signal processing perspective [J].

Gafni, Tomer ;

Shlezinger, Nir ;

Cohen, Kobi ;

Eldar, Yonina C. ;

Poor, H. Vincent .

IEEE SIGNAL PROCESSING MAGAZINE, 2022, 39 (03) :14-41

[7] Wireless Multi-Interface Connectivity with Deep Learning-Enabled User Devices: An Energy Efficiency Perspective [J].

Kaneko, Megumi ;

Ly Dinh, Thi Ha ;

Kawamura, Kenichi ;

Moriyama, Takatsune ;

Takatori, Yasushi .

IEEE NETWORK, 2023, 37 (03) :132-139

[8] Dynamic Channel Access and Power Control in Wireless Interference Networks via Multi-Agent Deep Reinforcement Learning [J].

Lu, Ziyang ;

Zhong, Chen ;

Gursoy, M. Cenk .

IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY, 2022, 71 (02) :1588-1601

[9] Federated Deep Reinforcement Learning for RIS-Assisted Indoor Multi-Robot Communication Systems [J].

Luo, Ruyu ;

Ni, Wanli ;

Tian, Hui ;

Cheng, Julian .

IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY, 2022, 71 (11) :12321-12326

[10]

McMahan HB, 2017, PR MACH LEARN RES, V54, P1273

← 1 2 →