Spectrum Access Model in Multi-Drone Networks via Cognitive Radio and Deep Reinforcement Learning for Optimized Communication and Efficiency
Keywords:
Deep Q-Networks (DQN), Proximal Policy Optimization (PPO), Orthogonal Frequency Division Multiple Access (OFDMA), Multiple-Input Multiple-Output (MIMO).Abstract
Cognitive Radio (CR), coupled with Deep Reinforcement Learning (DRL), has emerged as a promising technology for enhancing Dynamic Spectrum Access (DSA) in Multi-Drone Networks (MDNs). This paper explores the integration of CR with DRL for DSA in MDN, focusing on the utilization of cyclostationary feature detection in conjunction with advanced machine learning algorithms. The proposed framework leverages cyclostationary feature detection techniques to analyze spectral characteristics and identify vacant frequency bands, enabling MDNs to access unused spectrum resources opportunistically. Deep Q-Networks (DQN) and Proximal Policy Optimization (PPO) algorithms are employed for autonomous decision-making, allowing drones to learn optimal spectrum access strategies through trial-and-error interactions. Integrating Orthogonal Frequency Division Multiple Access (OFDMA) and Multiple-Input Multiple-Output (MIMO) systems enhances spectral efficiency and communication reliability in MDNs. Software Defined Networking (SDN) provides a flexible and programmable framework for dynamic network control and management, facilitating centralized spectrum management and coordination. Experimental evaluations demonstrate the effectiveness of the proposed approach in improving spectrum utilization, throughput, and overall network performance in MDNs. Through the synergistic combination of CR, DRL, cyclostationary feature detection, OFDMA, MIMO, and SDN technologies, this paper contributes to the advancement of intelligent spectrum management solutions for next-generation wireless networks. Experimental evaluations demonstrate the effectiveness of the proposed approach in improving spectrum utilization, throughput, and overall network performance in MDNs. Specifically, the achieved values include a 25% increase in spectrum utilization, a 30% improvement in throughput, and a 20% reduction in latency compared to baseline approaches.Top of Form
Downloads
References
Abbasi, M., Shahraki, A., Piran, M. J., & Taherkordi, A. (2021). Deep Reinforcement Learning for QoS provisioning at the MAC layer: A Survey. Engineering Applications of Artificial Intelligence, 102, 104234.
Khalek, N. A., Tashman, D. H., & Hamouda, W. (2023). Advances in Machine Learning-Driven Cognitive Radio for Wireless Networks: A Survey. IEEE Communications Surveys & Tutorials.
Murugan, S., & Sumithra, M. G. (2020). Big Data-Based Spectrum Sensing for Cognitive Radio Networks Using Artificial Intelligence. In Big Data Analytics for Sustainable Computing (pp. 146-159). IGI Global.
Oyewobi, S. S., Djouani, K., & Kurien, A. M. (2020). A review of industrial wireless communications, challenges, and solutions: A cognitive radio approach. Transactions on Emerging Telecommunications Technologies, 31(9), e4055.
Silva, B. N., Khan, M., & Han, K. (2018). Internet of things: A comprehensive review of enabling technologies, architecture, and challenges. IETE Technical review, 35(2), 205-220.
Arulappan, A., Mahanti, A., Passi, K., Thiruvenkadam, S., Naha, R., & Raja, G. (2024). DQN approach for Adaptive Self-healing of VNFs in Cloud-native Network. IEEE Access.
Li, X., Cheng, S., Ding, H., Pan, M., & Zhao, N. (2022). When UAVs meet cognitive radio: Offloading traffic under uncertain spectrum environment via deep reinforcement learning. IEEE Transactions on Wireless Communications, 22(2), 824-838.
Das, R., Khan, A., & Paul, G. (2024). A proximal policy optimization with curiosity algorithm for virtual drone navigation. Engineering Research Express, 6(1), 015057.
Harkat, H., Monteiro, P., Gameiro, A., Guiomar, F., & Farhana Thariq Ahmed, H. (2022). A survey on MIMO-OFDM systems: Review of recent trends. Signals, 3(2), 359-395.
Sarmiento, D. E., Lebre, A., Nussbaum, L., & Chari, A. (2021). Decentralized SDN control plane for a distributed cloud-edge infrastructure: A survey. IEEE Communications Surveys & Tutorials, 23(1), 256-281.
Goudarzi, S., Anisi, M. H., Ahmadi, H., & Musavian, L. (2020). Dynamic resource allocation model for distribution operations using SDN. IEEE internet of things journal, 8(2), 976-988.
Hamdi, W., Ksouri, C., Bulut, H., & Mosbah, M. (2024). Network Slicing Based Learning Techniques for IoV in 5G and Beyond Networks. IEEE Communications Surveys & Tutorials.
Lei, W., Ye, Y., & Xiao, M. (2020). Deep reinforcement learning-based spectrum allocation in integrated access and backhaul networks. IEEE Transactions on Cognitive Communications and Networking, 6(3), 970-979.
Zhao, D., Qin, H., Song, B., Han, B., Du, X., & Guizani, M. (2020). A graph convolutional network-based deep reinforcement learning approach for resource allocation in a cognitive radio network. Sensors, 20(18), 5216.
Bai, Y., Zhao, H., Zhang, X., Chang, Z., Jäntti, R., & Yang, K. (2023). Towards autonomous multi-UAV wireless network: A survey of reinforcement learning-based approaches. IEEE Communications Surveys & Tutorials.
Jana, S., Sudharani, B., SN, C. S., Vaishnavi, K., Aarthi, E., Chand, R., & Gopalakrishnan, S. (2024). Enhancing Face Recognition Performance: A Comprehensive Evaluation of Deep Learning Models and a Novel Ensemble Approach with Hyperparameter Tuning.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.
IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.
