An Adaptive Mac Protocol (DQ-MAC) for Efficient Dynamic Spectrum Access in Cognitive Radio Networks
DOI :
https://doi.org/10.62050/fscp2024.447Mots-clés :
Cognitive Radio, Dynamic Spectrum Access, DQN, Reinforcement Learning, Spectrum ManagementRésumé
Cognitive Radio Networks (CRNs) require dynamic spectrum access as a way to maximize the use of inadequate spectrum resources with minimal interference from licensed primary users. MAC protocols of a traditional nature frequently fail to respond effectively in real-time to changing channel availability, resulting in poor spectrum utilization and high rates of collisions. This work presents a new Deep Q-Network (DQN)-based MAC protocol that learns and adapts to the shifting spectrum environment, allowing secondary users to make insightful, instantaneous channel access choices. The development and assessment of the protocol occurred across different environments—urban, rural, and indoor—representing unique ranges of spectrum availability and interference issues. The simulations ran on MATLAB, utilizing actual user mobility, Rayleigh fading, interference, and noise conditions in the real world. Results show that the DQN-based MAC protocol markedly outperforms traditional random channel selection across major performance assessments, realizing up to 71% higher throughput, 58% less collisions, and improved equity within user interactions. The results show improvement in the spectrum efficiency and user performance in real time.
Références
I. F. Akyildiz, W.-Y. Lee, M. C. Vuran, and S. Mohanty, “A survey on spectrum management in cognitive radio networks,” IEEE Commun. Mag., vol. 46, no. 4, pp. 40–48, 2008.
Z. Zheng, S. Jiang, R. Feng, L. Ge, and C. Gu, “An adaptive backoff selection scheme based on Q-learning for CSMA/CA,” Wirel. Networks, vol. 29, no. 4, pp. 1899–1909, 2023, https://doi.org/10.1007/s11276-023-03257-0.
S. Haykin, “Cognitive radio: brain-empowered wireless communications,” IEEE J. Sel. areas Commun., vol. 23, no. 2, pp. 201–220, 2005.
M. Ali Shah, S. Zhang, and C. Maple, “An Analysis on Decentralized Adaptive MAC Protocols for Cognitive Radio Networks,” Int. J. Autom. Comput., vol. 10, no. 1, pp. 46–52, 2013, https://doi.org/10.1007/s11633-013-0695-z.
Y.-C. Liang, K.-C. Chen, G. Y. Li, and P. Mahonen, “Cognitive radio networking and communications: An overview,” IEEE Trans. Veh. Technol., vol. 60, no. 7, pp. 3386–3407, 2011.
M. Qiao, H. Zhao, S. Wang, and J. Wei, “MAC protocol selection based on machine learning in cognitive radio networks,” in 2016 19th International Symposium on Wireless Personal Multimedia Communications (WPMC), 2016, pp. 453–458.
Y. Xing, C. N. Mathur, M. A. Haleem, R. Chandramouli, and K. P. Subbalakshmi, “Dynamic spectrum access with QoS and interference temperature constraints,” IEEE Trans. Mob. Comput., vol. 6, no. 4, pp. 423–433, 2007.
R. S. Sutton and A. G. Barto, Reinforcement learning: An introduction, 1st ed. MIT press Cambridge, 2018.
V. Mnih et al., “Human-level control through deep reinforcement learning,” Nature, vol. 518, no. 7540, pp. 529–533, 2015.
B. T. Maharaj and B. S. Awoyemi, “Introduction to Cognitive Radio Networks,” in Developments in Cognitive Radio Networks, Cham: Springer International Publishing, 2022, pp. 3–12. https://doi.org/10.1007/978-3-030-64653-0_1.
E. Hossain, D. Niyato, and Z. Han, Dynamic spectrum access and management in cognitive radio networks. Cambridge university press, 2009.
A. Garhwal and P. P. Bhattacharya, “A survey on dynamic spectrum access techniques for cognitive radio,” arXiv Prepr. arXiv1201.1964, 2012.
Y. Lin, C. Wang, J. Wang, and Z. Dou, “A novel dynamic spectrum access framework based on reinforcement learning for cognitive radio sensor networks,” Sensors, vol. 16, no. 10, p. 1675, 2016.
Téléchargements
Publiée
Numéro
Rubrique
Licence
(c) Copyright Proceedings of the Faculty of Science Conferences 2025
Ce travail est disponible sous licence Creative Commons Attribution - Pas d’Utilisation Commerciale - Partage dans les Mêmes Conditions 4.0 International.
