Open Access Open Access  Restricted Access Subscription Access

Cognitive Radio Networks: AI-Driven Spectrum Optimization using Long Short-Term Memory and Machine Learning

F. O. Philip- Kpae, L. E. Ogbondamati, S. Kukuchuku

Abstract


The over dependent and demand for wireless communication network has necessitated efficient and effective spectrum utilization and network optimization. This study proposes an AI-driven Cognitive Radio Networks (CRNs) framework that integrates CRNs and Artificial Intelligence (AI) by leveraging machine learning (ML) and Long Short-Term Memory to Optimize spectrum management and overall network performance. The approach involves creating a model that uses AI and machine learning algorithms for dynamic spectrum allocation, capable of adapting to changing network conditions without human intervention. Quantitative results highlight the success of AI-driven CRNs in improving spectrum utilization. AI algorithms improved spectrum allocation efficiency by 20%, reduced interference by 15%, and boosted overall network throughput by 30%. Additionally, the study demonstrates that AI-powered CRNs can maintain network stability even during periods of high traffic, ensuring smooth communication with minimal latency. The research also touches on policy changes regarding spectrum regulation, advocating for more flexible and adaptive approaches to spectrum management. By demonstrating the practical advantages of AI in CRNs, this study contributes to efforts aimed at addressing the gap between limited spectrum availability and the growing demand for wireless connectivity. Ultimately, it offers valuable insights into the future of intelligent, adaptive wireless networks.


Full Text:

PDF

References


Abusubaih, M. A., & Khamayseh, S. (2021). Performance of machine learning-based techniques for spectrum sensing in mobile cognitive radio networks. IEEE Access, 10, 1410–1418. https://doi.org/.

Ahmad, M., Shafiq, M., Irshad, A., Afzal, M. K., Kim, D. W., & Choi, J.-G. (2018). Adaptive and economically-robust group selling of spectrum slots for cognitive radio-based networks. Sensors, 18, 2490. https://doi.org/.

Anatel. (2022). Approves the inspection procedure for verification of compliance with the commitments of scope and coverage area of the personal mobile service. Retrieved December 1, 2022, from https://informacoes.anatel.gov.br/legislacao/procedimentos-de-fiscalizacao/1724-portaria-2453.

Anatel. (2022). Mobile telephony—Cities served. Retrieved April 1, 2022, from https://www.gov.br/anatel/pt-br/regulado/universalizacao/telefonia-movel.

Aref, M. A., & Jayaweera, S. K. (2021). Spectrum-agile cognitive radios using multi-task transfer deep reinforcement learning. IEEE Transactions on Wireless Communications, 20, 6729–6742. https://doi.org/.

Corral-De-Witt, D., Ahmed, S., Awin, F., Rojo-Álvarez, J. L., & Tepe, K. (2019). An accurate probabilistic model for TVWS identification. Applied Sciences, 9, 4232. https://doi.org/.

Krasniqi, B., Bytyqi, G., & Statovci, D. (2018). Volte performance analysis and evaluation in real networks. In Proceedings of the 2nd International Balkan Conference on Communications and Networking (pp. 6–8). Podgorica, Montenegro.

Li, H., Ding, X., Yang, Y., Huang, X., & Zhang, G. (2019). Spectrum occupancy prediction for internet of things via long short-term memory. In Proceedings of the 2019 IEEE International Conference on Consumer Electronics-Taiwan (ICCE-TW) (1–2). Yilan, Taiwan.

Liu, X., & Zheng, K. (2022). Trade-offs among sensing, reporting, and transmission in cooperative CRNs. Sensors, 22, 4753. https://doi.org/.

Liu, X., Xu, B., Wang, X., Zheng, K., Chi, K., & Tian, X. (2022). Impacts of sensing energy and data availability on throughput of energy harvesting cognitive radio networks. IEEE Transactions on Vehicular Technology, 72, 747–759. https://doi.org/.


Refbacks

  • There are currently no refbacks.