Generalization of Deep Reinforcement Learning for Jammer-Resilient Frequency and Power Allocation

被引:0
作者
Kafle, Swatantra [1 ]
Jagannath, Jithin [1 ]
Kane, Zackary [1 ]
Biswas, Noor [1 ]
Kumar, Prem Sagar Vasanth [1 ]
Jagannath, Anu [1 ]
机构
[1] ANDRO Computat Solut LLC, Marconi Rosenblatt AI ML Innovat Lab, Rome, NY 13440 USA
关键词
Deep reinforcement learning; wireless network; power control; frequency selection; software-defined radio; ACCESS;
D O I
10.1109/LCOMM.2023.3274594
中图分类号
TN [电子技术、通信技术];
学科分类号
0809 ;
摘要
We tackle the problem of joint frequency and power allocation while emphasizing the generalization capability of a deep reinforcement learning model. Most of the existing methods solve reinforcement learning-based wireless problems for a specific pre-determined wireless network scenario. The performance of a trained agent tends to be very specific to the network and deteriorates when used in a different network operating scenario (e.g., different in size, neighborhood, and mobility, among others). We demonstrate our approach to enhance training to enable a higher generalization capability during inference of the deployed model in a distributed multi-agent setting in a hostile jamming environment. With all these, we show the improved training and inference performance of the proposed methods when tested on previously unseen simulated wireless networks of different sizes and architectures. More importantly, to prove practical impact, the end-to-end solution was implemented on the embedded software-defined radio and validated using over-the-air evaluation.
引用
收藏
页码:1789 / 1793
页数:5
相关论文
共 20 条
  • [1] Distributed Algorithms for Learning and Cognitive Medium Access with Logarithmic Regret
    Anandkumar, Animashree
    Michael, Nithin
    Tang, Kevin
    Swami, Ananthram
    [J]. IEEE JOURNAL ON SELECTED AREAS IN COMMUNICATIONS, 2011, 29 (04) : 731 - 745
  • [2] [Anonymous], 2023, OUTDOOR DEMONSTRATIO
  • [3] Marconi-Rosenblatt Framework for Intelligent Networks (MR-iNet Gym): For Rapid Design and Implementation of Distributed Multi-agent Reinforcement Learning Solutions for Wireless Networks
    Farquhar, Collin
    Kafle, Swatantra
    Hamedani, Kian
    Jagannath, Anu
    Jagannath, Jithin
    [J]. COMPUTER NETWORKS, 2023, 222
  • [4] ns-3 meets OpenAI Gym: The Playground for Machine Learning in Networking Research
    Gawlowicz, Piotr
    Zubow, Anatolij
    [J]. MSWIM'19: PROCEEDINGS OF THE 22ND INTERNATIONAL ACM CONFERENCE ON MODELING, ANALYSIS AND SIMULATION OF WIRELESS AND MOBILE SYSTEMS, 2019, : 113 - 120
  • [5] Ahmed KI, 2019, Arxiv, DOI arXiv:1904.13032
  • [6] Redefining Wireless Communication for 6G: Signal Processing Meets Deep Learning With Deep Unfolding
    Jagannath A.
    Jagannath J.
    Melodia T.
    [J]. Jagannath, Anu (anusaji1@gmail.com), 1600, Institute of Electrical and Electronics Engineers Inc. (02): : 528 - 536
  • [7] MR-iNet Gym: Framework for Edge Deployment of Deep Reinforcement Learning on Embedded Software Defined Radio
    Jagannath, Jithin
    Hamedani, Kian
    Farquhar, Collin
    Ramezanpour, Keyvan
    Jagannath, Anu
    [J]. PROCEEDINGS OF THE 2022 ACM WORKSHOP ON WIRELESS SECURITY AND MACHINE LEARNIG (WISEML '22), 2022, : 51 - 56
  • [8] Jagannath J, 2020, MACHINE LEARNING FOR FUTURE WIRELESS COMMUNICATIONS, P243
  • [9] Machine learning for wireless communications in the Internet of Things: A comprehensive survey
    Jagannath, Jithin
    Polosky, Nicholas
    Jagannath, Anu
    Restuccia, Francesco
    Melodia, Tommaso
    [J]. AD HOC NETWORKS, 2019, 93
  • [10] Intelligent Power Control for Spectrum Sharing in Cognitive Radios: A Deep Reinforcement Learning Approach
    Li, Xingjian
    Fang, Jun
    Cheng, Wen
    Duan, Huiping
    Chen, Zhi
    Li, Hongbin
    [J]. IEEE ACCESS, 2018, 6 : 25463 - 25473