Spectrum Access Model in Multi-Drone Networks via Cognitive Radio and Deep Reinforcement Learning for Optimized Communication and Efficiency

Authors

  • E. Srividhya, Vinoth Pandian, G. Vennila, G. Srinitya, P.K. Hemalatha, S. Muthumanickam

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

Download data is not yet available.

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

06.08.2024

How to Cite

E. Srividhya. (2024). Spectrum Access Model in Multi-Drone Networks via Cognitive Radio and Deep Reinforcement Learning for Optimized Communication and Efficiency. International Journal of Intelligent Systems and Applications in Engineering, 12(23s), 29–39. Retrieved from https://ijisae.org/index.php/IJISAE/article/view/6430

Issue

Section

Research Article