International Journal of Computational and Electronics Aspects in Engineering
Volume 7 · Issue 1 · February 2026 · pp. 45-57
Review Article · Peer Reviewed
Received: December 04, 2025 · Accepted: January 18, 2025 · Published: 04 February 2026
DOI: 10.26706/ijceae.7.1.20260104
Open Access · CC BY 4.0

AI-Driven Power Optimization in 6G Networks: A Comprehensive Review

Hussain Ali Mutar1*, Ibtihal R. N. ALRubeei2
1 Department of Computer Engineering, College of Computer Science and Information Technology, Wasit University, Wasit, Iraq
2 Department of Electrical Engineering, College of Engineering, Wasit University, Wasit, Iraq

*Corresponding author: hmutar@uowasit.edu.iq
Download PDF Cite this article Certificate Volume 7 Issue 1

Abstract

With sub-millisecond latency, connectivity of up to 10 million devices per square kilometre, and terabit-per-second data rates, sixth-generation (6G) wireless networks promise revolutionary performance. However, the accompanying surge in energy consumption presents a major challenge to sustainability and global carbon neutrality goals. Consequently, power optimization has become a core design requirement for 6G systems.

This comprehensive review synthesizes and critically evaluates recent research on AI-driven power optimization in 6G networks, positioning artificial intelligence as the primary enabler of intelligent, adaptive, and autonomous energy management. The methodology is based on a systematic analysis of more than 130 research articles, surveys, and standards documents published between 2019 and 2025.

Key AI techniques—including Deep Learning (DL), Reinforcement Learning (RL), Federated Learning (FL), and Graph Neural Networks (GNNs)—are categorized and analyzed alongside emerging concepts such as AI-native network slicing, reconfigurable intelligent surface (RIS) optimization, and dynamic resource allocation. Reported results indicate that AI-based approaches can consistently reduce energy consumption by 20–40% while maintaining QoS requirements, with some studies demonstrating savings up to 60% and spectral efficiency gains of 29%.

In addition to achievements, this paper examines performance trade-offs, including computational complexity, privacy–accuracy balance in distributed learning, and scalability in ultra-dense network environments. Persistent challenges such as data scarcity, model interoperability, security risks, and the environmental impact of AI training are also discussed. Finally, the paper outlines future research directions encompassing smart energy grid integration, digital-twin-based evaluation, explainable AI (XAI), quantum-assisted optimization, and deep cross-layer intelligence. This work serves as a strategic roadmap for developing sustainable, high-performance, and truly intelligent 6G networks.

Keywords

Power Optimization 6G Networks Energy Efficiency Artificial Intelligence (AI) Ultra-Dense Networks Performance Trade-offs

References

References

  1. H. F. Alhashimi et al., “Survey on AI-Enabled Resource Management for 6G Heterogeneous Networks: Recent Research, Challenges, and Future Trends,” Computers, Materials and Continua, vol. 83, no. 3, pp. 3585–3622, 2025. doi: 10.32604/cmc.2025.062867.
  2. T. Huang, W. Yang, J. Wu, J. Ma, X. Zhang, and D. Zhang, “A survey on green 6G network: Architecture and technologies,” IEEE Access, vol. 7, pp. 175758–175768, 2019. doi: 10.1109/ACCESS.2019.2957648.
  3. Z. Hasan, H. Boostanimehr, and V. K. Bhargava, “Green Cellular Networks: A Survey, Some Research Issues and Challenges,” IEEE Communications Surveys & Tutorials, vol. 13, no. 4, pp. 524–540, 2011. doi: 10.1109/SURV.2011.092311.00031.
  4. G. Auer et al., “How much energy is needed to run a wireless network?,” IEEE Wireless Communications, vol. 18, 2012.
  5. F. Xie, “AI-Powered 6G Network Energy Efficiency Optimization: A Survey,” Scientific Journal of Intelligent Systems Research, vol. 7, no. 12, pp. 46–53, 2025. doi: 10.54691/6vjqdn45.
  6. K. Noor, A. L. Imoize, M. A. Adelabu, and C.-C. Lee, “A Comprehensive Survey on AI-Assisted Multiple Access Enablers for 6G and Beyond Wireless Networks,” CMES – Computer Modeling in Engineering and Sciences, vol. 145, no. 2, pp. 1575–1664, 2025. doi: 10.32604/cmes.2025.073200.
  7. Y. Sanjalawe et al., “AI-Powered Smart Grids in the 6G Era: A Comprehensive Survey on Security and Intelligent Energy Systems,” IEEE Open Journal of the Communications Society, vol. 6, pp. 7677–7719, 2025. doi: 10.1109/OJCOMS.2025.3609144.
  8. B. R. Das et al., “A Comprehensive Survey on Emerging AI Technologies for 6G Communications,” International Journal of Intelligent Networks, vol. 6, pp. 113–150, 2025. doi: 10.1016/j.ijin.2025.06.001.
  9. W. Jiang, B. Han, M. A. Habibi, and H. D. Schotten, “The Road Towards 6G: A Comprehensive Survey,” IEEE Open Journal of the Communications Society, vol. 2, pp. 334–366, 2021. doi: 10.1109/OJCOMS.2021.3057679.
  10. R. Kamran et al., “Energy-Aware 6G Network Design: A Survey,” arXiv preprint, arXiv:2509.11289, 2025. doi: 10.48550/arXiv.2509.11289.
  11. C. Han and S. Armour, “Energy efficient radio resource management strategies for green radio,” IET Communications, vol. 5, pp. 2629–2639, 2011. doi: 10.1049/iet-com.2011.0113.
  12. H. F. Alhashimi et al., “A Survey on Resource Management for 6G Heterogeneous Networks,” Electronics, vol. 12, no. 3, p. 647, 2023. doi: 10.3390/electronics12030647.
  13. W. Y. B. Lim et al., “Federated Learning in Mobile Edge Networks,” IEEE Communications Surveys & Tutorials, vol. 22, no. 3, pp. 2031–2063, 2020. doi: 10.1109/COMST.2020.2986024.
  14. N. C. Luong et al., “Applications of Deep Reinforcement Learning in Communications and Networking,” IEEE Communications Surveys & Tutorials, vol. 21, no. 4, pp. 3133–3174, 2019. doi: 10.1109/COMST.2019.2916583.
  15. A. Barredo Arrieta et al., “Explainable Artificial Intelligence (XAI),” Information Fusion, vol. 58, pp. 82–115, 2020. doi: 10.1016/j.inffus.2019.12.012.
  16. B. Mao, J. Liu, Y. Wu, and N. Kato, “Security and Privacy on 6G Network Edge: A Survey,” IEEE Communications Surveys & Tutorials, vol. 25, no. 2, pp. 1095–1127, 2023. doi: 10.1109/COMST.2023.3244674.
  17. H. Shen, K. Zhang, M. Hong, and T. Chen, “Towards Understanding Asynchronous Advantage Actor-Critic,” IEEE Transactions on Signal Processing, vol. 71, pp. 2579–2594, 2023. doi: 10.1109/TSP.2023.3268475.
  18. L. Jiao et al., “Advanced Deep Learning Models for 6G,” IEEE Access, vol. 12, pp. 133245–133314, 2024. doi: 10.1109/ACCESS.2024.3418900.
  19. V. Vishnoi et al., “Multiagent Deep Reinforcement Learning-Based Energy Efficient Resource Management,” Alexandria Engineering Journal, vol. 116, pp. 609–620, 2025. doi: 10.1016/j.aej.2024.12.004.
  20. L. Feng et al., “Double-Timescale Multi-Agent Deep Reinforcement Learning,” Electronics, vol. 13, no. 14, p. 2764, 2024. doi: 10.3390/electronics13142764.
  21. M. M. Rashid et al., “Federated Learning-Based Intrusion Detection,” Network, vol. 3, no. 1, pp. 158–179, 2023. doi: 10.3390/network3010008.
  22. W. Ma, C. Qi, and G. Li, “Machine Learning for Beam Alignment,” IEEE Wireless Communications Letters, 2020. doi: 10.1109/LWC.2020.2973972.
  23. Y. Liu et al., “Nonorthogonal Multiple Access for 5G and Beyond,” Proceedings of the IEEE, vol. 105, no. 12, pp. 2347–2381, 2017. doi: 10.1109/JPROC.2017.2768666.
  24. V. E. Jyothi et al., “Adaptive Cloud Load Balancing with Reinforcement Learning,” in Proc. ICESC, 2024, pp. 572–579. doi: 10.1109/ICESC60852.2024.10689973.
  25. W. A. Aziz et al., “Content-Aware Network Traffic Prediction,” IEEE Access, vol. 11, pp. 99716–99733, 2023. doi: 10.1109/ACCESS.2023.3309002.
  26. D. Abode, R. Adeogun, and G. Berardinelli, “Power Control for 6G Industrial Wireless Subnetworks,” in Proc. IEEE WCNC, 2023, pp. 1–6. doi: 10.1109/WCNC55385.2023.10118984.
  27. M. Z. Chowdhury et al., “6G Wireless Communication Systems,” IEEE Open Journal of the Communications Society, vol. 1, pp. 957–975, 2020. doi: 10.1109/OJCOMS.2020.3010270.
  28. E. C. Strinati et al., “6G: The Next Frontier,” IEEE Vehicular Technology Magazine, vol. 14, no. 3, pp. 42–50, 2019. doi: 10.1109/MVT.2019.2921162.
  29. S. Dang et al., “What should 6G be?,” Nature Electronics, vol. 3, pp. 20–29, 2020. doi: 10.1038/s41928-019-0355-6.
  30. O. Giwa et al., “Meta-Reinforcement Learning for Spectrum Allocation,” arXiv preprint, arXiv:2507.10619, 2025. doi: 10.48550/arXiv.2507.10619.
  31. L. Wang et al., “Deep Reinforcement Learning-Based Adaptive Handover,” IEEE Access, vol. 9, pp. 87241–87250, 2021. doi: 10.1109/ACCESS.2021.3089521.
  32. H. Tang et al., “Double Deep Q-Network Based Dynamic Framing,” IEEE Transactions on Network Science and Engineering, vol. 10, no. 3, pp. 1297–1310, 2023. doi: 10.1109/TNSE.2022.3172794.
  33. M. Maleki et al., “Model-Based Reinforcement Learning for Routing,” Wireless Personal Communications, vol. 95, no. 3, pp. 3119–3139, 2017. doi: 10.1007/s11277-017-3987-8.
  34. Y. An et al., “Deep Learning-Based Lightweight CSI Feedback,” Physical Communication, vol. 68, p. 102538, 2025. doi: 10.1016/j.phycom.2024.102538.
  35. H. Yang et al., “Distributed Deep Reinforcement Learning-Based Spectrum Allocation,” IEEE Transactions on Wireless Communications, vol. 21, no. 9, pp. 6935–6948, 2022. doi: 10.1109/TWC.2022.3153175.
  36. S. Liu et al., “Federated Learning and Deep Reinforcement Learning,” Sensors, vol. 23, no. 4, p. 2243, 2023. doi: 10.3390/s23042243.
  37. S. Ali et al., “DL-Based Joint Resource Allocation,” IEEE Access, vol. 9, pp. 118357–118366, 2021. doi: 10.1109/ACCESS.2021.3107430.
  38. J. Zhou et al., “Graph Neural Networks: A Review,” AI Open, vol. 1, pp. 57–81, 2020. doi: 10.1016/j.aiopen.2021.01.001.
  39. M. Eisen and A. Ribeiro, “Optimal Wireless Resource Allocation With GNNs,” IEEE Transactions on Signal Processing, vol. 68, pp. 2977–2991, 2020. doi: 10.1109/TSP.2020.2988255.
  40. Y. Shen et al., “Graph Neural Networks for Scalable RRM,” IEEE Journal on Selected Areas in Communications, vol. 39, no. 1, pp. 101–115, 2021. doi: 10.1109/JSAC.2020.3036965.
  41. H. Zhao, “Privacy Protection and Performance Optimization in 6G,” Discover Artificial Intelligence, vol. 6, no. 1, p. 41, 2025. doi: 10.1007/s44163-025-00687-x.
  42. P. Kairouz and H. B. McMahan, “Advances and Open Problems in Federated Learning,” Foundations and Trends in Machine Learning, vol. 14, no. 1–2, pp. 1–210, 2021. doi: 10.1561/2200000083.
  43. Y. Lin et al., “Federated Learning Over Wireless Networks,” IEEE Transactions on Wireless Communications, 2026. doi: 10.1109/TWC.2025.3611589.
  44. I. A. Bartsiokas et al., “Federated Learning for 6G HetNets,” in Encyclopedia of Information Science and Technology, IGI Global, 2025, pp. 1–28.
  45. Z. Wang et al., “Federated Continual Learning for Edge-AI,” arXiv preprint, arXiv:2411.13740, 2024. doi: 10.48550/arXiv.2411.13740.
  46. D. Shome et al., “Federated Learning and Next Generation Wireless Communications,” Transactions on Emerging Telecommunications Technologies, vol. 33, no. 7, p. e4458, 2022. doi: 10.1002/ett.4458.
  47. H. Chen et al., “Federated Learning Over Wireless IoT Networks,” IEEE Internet of Things Journal, vol. 9, no. 17, pp. 16592–16605, 2022. doi: 10.1109/JIOT.2022.3151193.
  48. M. Chen et al., “Communication-Efficient Federated Learning,” PNAS, vol. 118, no. 17, 2021. doi: 10.1073/pnas.2024789118.
  49. B. Agarwal et al., “Survey on Radio Resource Management in 5G HetNets,” IEEE Communications Surveys & Tutorials, vol. 24, no. 4, pp. 2495–2534, 2022. doi: 10.1109/COMST.2022.3207967.
  50. T. Hu et al., “Network Slicing via Transfer Learning,” in Proc. IEEE GLOBECOM, 2022, pp. 2909–2914. doi: 10.1109/GLOBECOM48099.2022.10000763.
  51. H. Wang and B. Li, “Double-Deep Q-Learning-Based Handover Management,” Transactions on Emerging Telecommunications Technologies, vol. 35, no. 1, p. e4907, 2024. doi: 10.1002/ett.4907.
  52. S. N. Ibrahim et al., “Asynchronous Advantage Actor-Critic for Smart Buildings,” SSRN, 2024. doi: 10.2139/ssrn.4749398.
  53. A. A. Khalil et al., “Deep Learning-Based Energy Harvesting,” Computer Networks, vol. 229, p. 109784, 2023. doi: 10.1016/j.comnet.2023.109784.
  54. T. H. Moges et al., “Age of Information-Aware UAV Trajectory Optimization,” Computer Networks, vol. 268, p. 111369, 2025. doi: 10.1016/j.comnet.2025.111369.
  55. Y. Motokawa and T. Sugawara, “Distributed Multi-Agent Deep Reinforcement Learning,” in Proc. IJCNN, 2022. doi: 10.1109/IJCNN55064.2022.9892253.
  56. Y. Wang et al., “Federated Multi-Agent DRL-Based Pricing,” IEEE Transactions on Energy Markets, Policy and Regulation, vol. 3, no. 3, pp. 363–375, 2025. doi: 10.1109/TEMPR.2025.3558414.
  57. A. Jarwan and M. Ibnkahla, “Edge-Based Federated DRL for IoT,” IEEE Internet of Things Journal, vol. 10, no. 5, pp. 3799–3813, 2023. doi: 10.1109/JIOT.2022.3174469.
  58. J. Kim, Y. Cho, and J. Kim, “Edge Convolution GNN Assisted Power Allocation,” IEEE Access, vol. 12, pp. 129928–129939, 2024. doi: 10.1109/ACCESS.2024.3457805.
  59. Z. Wang, M. Eisen, and A. Ribeiro, “Learning Decentralized Wireless Resource Allocations,” IEEE Transactions on Signal Processing, vol. 70, 2022. doi: 10.1109/TSP.2022.3163626.
  60. Y. Shen et al., Graph Neural Networks for Wireless Communications, Cambridge Univ. Press, 2022.
  61. R. Rischke et al., “Federated Learning in Dentistry,” Journal of Dental Research, vol. 101, no. 11, pp. 1269–1273, 2022. doi: 10.1177/00220345221108953.
  62. H.-S. Lee and D.-E. Lee, “Resource Allocation with Federated Learning,” ICT Express, vol. 8, no. 1, pp. 31–36, 2022. doi: 10.1016/j.icte.2022.01.019.
  63. S. N. Karahan and O. Kaya, “Federated Learning-Based Intrusion Detection,” in Proc. AICCONF, 2025. doi: 10.1109/AICCONF64766.2025.11064190.
  64. S. K. Das et al., “Federated Reinforcement Learning for Wireless Networks,” IEEE Open Journal of Vehicular Technology, vol. 5, pp. 1400–1440, 2024. doi: 10.1109/OJVT.2024.3466858.
  65. D. C. Nguyen et al., “Federated Learning for IoT,” IEEE Communications Surveys & Tutorials, vol. 23, no. 3, pp. 1622–1658, 2021. doi: 10.1109/COMST.2021.3075439.
  66. A. Reisizadeh et al., “FedPAQ,” in Proc. AISTATS, 2020.
  67. X. Li et al., “On the Convergence of FedAvg,” arXiv preprint, arXiv:1907.02189, 2019. doi: 10.48550/arXiv.1907.02189.
  68. S. Savazzi et al., “Federated Learning With Cooperating Devices,” IEEE Internet of Things Journal, vol. 7, no. 5, pp. 4641–4654, 2020. doi: 10.1109/JIOT.2020.2964162.
  69. M. M. Amiri and D. Gündüz, “Federated Learning Over Wireless Fading Channels,” IEEE Transactions on Wireless Communications, vol. 19, no. 5, pp. 3546–3557, 2020. doi: 10.1109/TWC.2020.2974748.
  70. K. Bonawitz et al., “Towards Federated Learning at Scale,” Proc. MLSys, vol. 1, pp. 374–388, 2019.
  71. L. Melis et al., “Exploiting Unintended Feature Leakage,” in Proc. IEEE S&P, 2019. doi: 10.1109/SP.2019.00029.
  72. R. Zhang et al., “Model-Based GNN Enabled Energy-Efficient Beamforming,” IEEE Transactions on Wireless Communications, vol. 24, no. 4, pp. 3333–3345, 2025. doi: 10.1109/TWC.2025.3530003.
  73. R. Ramli and B. M. Lee, “Deep Learning for Resource Management in mmWave-NOMA,” IEEE Access, vol. 12, pp. 167883–167905, 2024. doi: 10.1109/ACCESS.2024.3497137.
  74. S. S. Sefati et al., “Resource Management in 6G IoT Networks,” IEEE Access, vol. 12, pp. 113741–113784, 2024. doi: 10.1109/ACCESS.2024.3444313.
  75. H. Kim, “Dynamic Resource Allocation for 6G Metaverse,” in Proc. ICAIIC, 2024. doi: 10.1109/ICAIIC60209.2024.10463509.
  76. K. R. Balmuri et al., “LSTM-Based Radio Resource Management,” Future Internet, vol. 14, no. 6, p. 184, 2022. doi: 10.3390/fi14060184.
  77. H. A. Mutar et al., “Hybrid Neural Network–Genetic Algorithm Framework,” 2026. doi: 10.53759/7669/jmc202606021.
  78. I. R. ALRubeei et al., “AI for Enhancement of Solar Cell Efficiency,” 2025.
  79. W. Wu et al., “AI-Native Network Slicing for 6G,” IEEE Wireless Communications, vol. 29, no. 1, pp. 96–103, 2022. doi: 10.1109/MWC.001.2100338.
  80. M. S. Khan et al., “Explainable AI Decision Stack Framework,” Biomimetics, vol. 7, no. 3, p. 127, 2022. doi: 10.3390/biomimetics7030127.
  81. R. Sohaib et al., “Network Slicing for Beyond 5G,” Electronics, vol. 10, p. 1090, 2021. doi: 10.3390/electronics10091090.
  82. E. Strubell et al., “Energy and Policy Considerations for Deep Learning,” in Proc. ACL, 2019, pp. 3645–3650. doi: 10.18653/v1/P19-1355.
  83. M. K. Abdul-Hussein et al., “Interference Communication System Using IoT,” in Recent Trends and Applications of Soft Computing, Springer, 2024, pp. 69–82. doi: 10.1007/978-3-031-82881-2_5.