Radio Resource Management in 5G and Beyond Networks: A Layered In-network Learning Approach

5G 及其他网络中的无线电资源管理：分层网络内学习方法

• 批准号: 20K11764
• 负责人: 王 瀟岩
• 金额: $ 2.75万
• 依托单位: Ibaraki University
• 依托单位国家: 日本
• 项目类别: Grant-in-Aid for Scientific Research (C)
• 财政年份: 2020
• 资助国家: 日本
• 起止时间: 2020-04-01 至 2024-03-31
• 项目状态: 已结题
• 来源: https://kaken.nii.ac.jp/en/grant/KAKENHI-PROJECT-20K11764/
• 关键词: wireless access; federated learning; reinforcement learning; In-network learning; radio resource

In FY2022, we investigate the practical global model update process in wireless networks by proposing a robust asynchronized computing and communication process. Specifically, we proposed to decouple the computing and communication processes, and let the edge server use a subset of asynchronized local gradients to update the global model. We proved the algorithm’s convergence and evaluated its performance by simulations.

在2022财年，我们通过提出稳健的简化计算和通信流程，研究无线网络中的实际全局模型更新流程。具体来说，我们提出将计算和通信过程解耦，并让边缘服务器使用局部梯度的子集来更新全局模型。我们证明了算法的收敛性，并通过仿真评估其性能。

项目成果

Wireless Access Control in Edge-Aided Disaster Response: A Deep Reinforcement Learning-Based Approach

• DOI: 10.1109/access.2021.3067662
• 发表时间: 2021
• 期刊: IEEE Access
• 影响因子: 3.9
• 作者: Hang Zhou;Xiaoyan Wang;M. Umehira;Xianfu Chen;Celimuge Wu;Yusheng Ji

Deep reinforcement learning based secondary user transmit power control for underlay cognitive radio networks

• DOI: 10.1145/3538641.3561484
• 发表时间: 2022-10
• 期刊: Proceedings of the Conference on Research in Adaptive and Convergent Systems
• 作者: Kouhei Katou;Xiaoyan Wang;M. Umehira;Yusheng Ji

When Vehicular Fog Computing Meets Autonomous Driving: Computational Resource Management and Task Offloading

• DOI: 10.1109/mnet.001.1900527
• 发表时间: 2020-11
• 期刊: IEEE Network
• 影响因子: 9.3
• 作者: Zhenyu Zhou;Haijun Liao;Xiaoyan Wang;S. Mumtaz;Jonathan Rodriguez

Asynchronous Federated Deep Reinforcement Learning-Based URLLC-Aware Computation Offloading in Space-Assisted Vehicular Networks

• DOI: 10.1109/tits.2022.3150756
• 发表时间: 2022-02-24
• 期刊: IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
• 影响因子: 8.5
• 作者: Pan, Chao;Wang, Zhao;Al-Otaibi, Sattam
• 通讯作者: Al-Otaibi, Sattam

Deep Reinforcement Learning based Access Control for Disaster Response Networks

• DOI: 10.1109/globecom42002.2020.9322553
• 发表时间: 2020-12
• 期刊: GLOBECOM 2020 - 2020 IEEE Global Communications Conference
• 作者: Hang Zhou;Xiaoyan Wang;M. Umehira;Xianfu Chen;Celimuge Wu;Yusheng Ji