AI-Based Power Control for Solar-Powered OFDM Systems

Abdulkafi, Ayad; Hardan, Ibrahim

doi:10.25673/121716

Proceedings of International Conference on Applied Innovation in IT · 2025/08/29 · Vol. 13 · Issue 4 · pp. 27–32

AI-Based Power Control for Solar-Powered OFDM Systems

Ayad A. Abdulkafi, Ibrahim K. Sileh and Saad M. Hardan

📄 Download PDF DOI: 10.25673/121716

Abstract

This paper explores the integration of renewable energy and artificial intelligence (AI) into next-generation wireless communication networks. Using orthogonal frequency-division multiplexing (OFDM) over Rayleigh fading channels, we simulate and evaluate four scenarios: traditional wireless systems, renewable-powered systems, AI-assisted systems, and intelligent renewable-powered systems. Key performance metrics such as Bit Error Rate (BER), Spectral Efficiency (SE), and Energy Efficiency (EE) are analyzed under varying signal-to-noise ratio (SNR) conditions. A Q-learning-based AI algorithm is employed for dynamic power allocation, aiming to maximize energy efficiency while preserving communication reliability. Simulation results show that AI-assisted renewable-powered systems—especially those powered by solar energy—offer significant improvements in energy efficiency without degrading signal performance. The findings underscore the potential of combining AI and renewable energy to build sustainable, efficient, and reliable wireless networks. This study supports the vision of intelligent, green 6G and beyond communication systems, where environmental sustainability and high performance are jointly achieved through advanced optimization and clean energy integration.

Keywords

Energy Efficiency Wireless Network AI; Q-learning OFDM.

References

Ericsson, 6G – Connecting a Cyber-Physical World, [Online]. Available: https://www.ericsson.com/en/6g.
Telecom Review Africa, "6G expected to emerge by 2030," [Online]. Available: https://www.telecomreviewafrica.com.
Data Center Dynamics, "6G and spectrum: Planning for the next generation," [Online]. Available: https://www.datacenterdynamics.com.
M. H. Alsharif, A. A. Alsharif, M. A. Albreem, A. S. Alofi, and M. S. Hossain, "Energy-efficient 6G networks: Emerging trends and challenges," Sensors, vol. 22, no. 13, pp. 1–26, 2022.
E. Bedeer, O. A. Dobre, and K. E. Baddour, "Energy-efficient power loading for OFDM-based cognitive radio systems with channel and power allocation," IEEE Trans. Wireless Commun., vol. 13, no. 3, pp. 1302–1312, Mar. 2014.
A. Goldsmith, Wireless Communications. Cambridge, U.K.: Cambridge Univ. Press, 2005.
R. S. Sutton and A. G. Barto, Reinforcement Learning: An Introduction, 2nd ed. Cambridge, MA, USA: MIT Press, 2018.
Y. Nasser, M. Ibrahim, T. Elfouly, and H. Refai, "Deep Q-learning–based resource allocation for solar-powered users in cognitive radio networks," Comput. Netw., vol. 198, p. 108376, 2021.
S. Shveta and N. A. Priyadharsini, "Q Learning based Power Allocation for Near and Far Users in 6G Cell Free Networks," International Journal of Innovative Research in Technology, vol. 11, no. 3, pp. 1280–1283, Aug. 2024.
A. A. Shabbir, M. F. Shirazi, S. Rizvi, S. Ahmad, and A. A. Ateya, "Energy efficiency and load optimization in heterogeneous networks through dynamic sleep strategies: A constraint-based optimization approach," Future Internet, vol. 16, no. 8, art. 262, Jul. 2024, [Online]. Available: https://doi.org/10.3390/fi16080262.
A. A. Abdulkafi, D. Chieng, and A. A. Abdulkafi, "Energy-aware load adaptive framework for LTE heterogeneous network," Australian Journal of Basic and Applied Sciences, vol. 7, no. 7, pp. 404–413, 2013.