Deep reinforcement learning agents for dynamic spectrum access in television whitespace cognitive radio networks

被引:0
|
作者
Ukpong, Udeme C. [1 ,2 ]
Idowu-Bismark, Olabode [1 ,2 ]
Adetiba, Emmanuel [1 ,2 ,5 ]
Kala, Jules R. [3 ]
Owolabi, Emmanuel [4 ]
Oshin, Oluwadamilola [1 ,2 ]
Abayomi, Abdultaofeek [6 ,7 ]
Dare, Oluwatobi E. [1 ,2 ]
机构
[1] Covenant Univ, Dept Elect & Informat Engn, Ota, Nigeria
[2] Covenant Univ, Covenant Appl Informat & Commun African Ctr Excell, Ota, Nigeria
[3] Int Univ Grand Bassam, Grand Bassam, Cote Ivoire
[4] Univ Pretoria, Pretoria, South Africa
[5] Durban Univ Technol, Inst Syst Sci, HRA, Durban, South Africa
[6] Walter Sisulu Univ, HRA, ZA-5200 East London, South Africa
[7] Summit Univ, Innovat & Adv Sci Res Grp IASRG, PMB 4412, Offa, Kwara, Nigeria
关键词
Cognitive radio networks; Deep reinforcement learning; DQN; Dynamic spectrum access; QR-DQN; Television whitespace; RFRL gym; MULTIPLE-ACCESS; ALLOCATION;
D O I
10.1016/j.sciaf.2024.e02523
中图分类号
O [数理科学和化学]; P [天文学、地球科学]; Q [生物科学]; N [自然科学总论];
学科分类号
07 ; 0710 ; 09 ;
摘要
Businesses, security agencies, institutions, and individuals depend on wireless communication to run their day-to-day activities successfully. The ever-increasing demand for wireless communication services, coupled with the scarcity of available radio frequency spectrum, necessitates innovative approaches to spectrum management. Cognitive Radio (CR) technology has emerged as a pivotal solution, enabling dynamic spectrum sharing among secondary users while respecting the rights of primary users. However, the basic setup of CR technology is insufficient to manage spectrum congestion, as it lacks the ability to predict future spectrum holes, leading to interferences. With predictive intelligence and Dynamic Spectrum Access (DSA), a CR can anticipate when and where other users will be using the radio frequency spectrum, allowing it to overcome this limitation. Reinforcement Learning (RL) in CRs helps predict spectral changes and identify optimal transmission frequencies. This work presents the development of Deep RL (DRL) models for enhanced DSA in TV Whitespace (TVWS) cognitive radio networks using Deep QNetworks (DQN) and Quantile-Regression (QR-DQN) algorithms. The implementation was done in the Radio Frequency Reinforcement Learning (RFRL) Gym, a training environment of the RF spectrum designed to provide comprehensive functionality. Evaluations show that the DQN model achieves a 96.34 % interference avoidance rate compared to 95.97 % of QRDQN. Average latency was estimated at 1 millisecond and 3.33 milliseconds per packet, respectively. Therefore DRL proves to be a more flexible, scalable, and adaptive approach to dynamic spectrum access, making it particularly effective in the complex and constantly evolving wireless spectrum environment.
引用
收藏
页数:16
相关论文
共 50 条
  • [21] Deep Reinforcement Learning for Dynamic Radio Access Selection over Future Wireless Networks
    Carballo Gonzalez, Claudia
    Fontes Pupo, Ernesto
    Pereira-Ruisanchez, Dariel
    Atzori, Luigi
    Murroni, Maurizio
    2022 IEEE INTERNATIONAL SYMPOSIUM ON BROADBAND MULTIMEDIA SYSTEMS AND BROADCASTING (BMSB), 2022,
  • [22] Deep Reinforcement Learning Based Dynamic Resource Allocation in Cloud Radio Access Networks
    Rodoshi, Rehenuma Tasnim
    Kim, Taewoon
    Choi, Wooyeol
    11TH INTERNATIONAL CONFERENCE ON ICT CONVERGENCE: DATA, NETWORK, AND AI IN THE AGE OF UNTACT (ICTC 2020), 2020, : 618 - 623
  • [23] A survey of dynamic spectrum allocation based on reinforcement learning algorithms in cognitive radio networks
    Wang, Yonghua
    Ye, Zifeng
    Wan, Pin
    Zhao, Jiajun
    ARTIFICIAL INTELLIGENCE REVIEW, 2019, 51 (03) : 493 - 506
  • [24] Deep-Reinforcement Learning for Fair Distributed Dynamic Spectrum Access in Wireless Networks
    Janiar, Siavash Barqi
    Pourahmadi, Vahid
    2021 IEEE 18TH ANNUAL CONSUMER COMMUNICATIONS & NETWORKING CONFERENCE (CCNC), 2021,
  • [25] A Deep Reinforcement Learning Framework for Spectrum Management in Dynamic Spectrum Access
    Song, Hao
    Liu, Lingjia
    Ashdown, Jonathan
    Yi, Yang
    IEEE INTERNET OF THINGS JOURNAL, 2021, 8 (14): : 11208 - 11218
  • [26] A comprehensive survey on machine learning approaches for dynamic spectrum access in cognitive radio networks
    Kaur, Amandeep
    Kumar, Krishan
    JOURNAL OF EXPERIMENTAL & THEORETICAL ARTIFICIAL INTELLIGENCE, 2022, 34 (01) : 1 - 40
  • [27] Deep-Q Reinforcement Learning for Fairness in Multiple-Access Cognitive Radio Networks
    Ali, Zain
    Rezki, Zouheir
    Sadjadpour, Hamid
    2022 IEEE WIRELESS COMMUNICATIONS AND NETWORKING CONFERENCE (WCNC), 2022, : 2023 - 2028
  • [28] Deep Reinforcement Learning Based Dynamic Spectrum Competition in Green Cognitive Virtualized Networks
    Quang Vinh Do
    Koo, Insoo
    IEEE ACCESS, 2021, 9 : 52193 - 52201
  • [29] Multiagent reinforcement learning dynamic spectrum access in cognitive radios
    Chun, Wu
    Mingyong, Yin
    Shaoliang, Ma
    Hong, Jiang
    Sensors and Transducers, 2014, 164 (02): : 170 - 175
  • [30] Dynamic Spectrum Access with QoS Provisioning in Cognitive Radio Networks
    An, Chunyan
    Ji, Hong
    Si, Pengbo
    2010 IEEE GLOBAL TELECOMMUNICATIONS CONFERENCE GLOBECOM 2010, 2010,