A Review of Deep Reinforcement Learning-Based Energy Saving for 6G Network

Tao Weng

doi:10.54691/djh92963

Authors

Tao Weng Nanjing University Of Posts And Telecommunications, Nanjing, 210023, China

DOI:

https://doi.org/10.54691/djh92963

Keywords:

6G Network, energy saving, deep reinforcement learning.

Abstract

With the exponential enhancement of 6G network performance, its energy consumption has become a core challenge constraining sustainable development. This paper systematically surveys the research progress of Deep Reinforcement Learning (DRL) in the field of 6G energy saving, focusing on three key technologies: resource scheduling, power control, and sleep strategies. It analyzes the application effects in typical scenarios such as ultra-dense urban networks, Space Air Ground Sea Integrated Networks (SAGIN), and Industrial Internet of Things (IIoT). Our analysis indicates that DRL, utilizing its autonomous decision-making and optimization capabilities, can effectively address the high dynamics and resource coupling inherent in 6G environments. However, bottlenecks still exist, including policy lag and long-term credit assignment. Future research directions need to make breakthroughs in dynamic coordination of renewable energy sources, lightweight engineering deployment, and cross-scenario generalization through meta-learning. This survey an attempt to construct a DRL driven 6G energy-saving technology system framework, providing a theoretical foundation for academia and industry to collaboratively advance high-performance, low-energy-consumption 6G networks.

Downloads

Download data is not yet available.

References

[1] J. Sanusi, O. Oshiga, S. Thomas, S. Idris, S. Adeshina, and A. M. Abba, ‘A Review on 6G Wireless Communication Systems: Localization and Sensing’, in 2021 1st International Conference on Multidisciplinary Engineering and Applied Science (ICMEAS), July 2021, pp. 1–5. doi: 10.1109/ICMEAS52683.2021.9692415.

[2] L. Jiao et al., ‘Advanced Deep Learning Models for 6G: Overview, Opportunities, and Challenges’, IEEE Access, vol. 12, pp. 133245–133314, 2024, doi: 10.1109/ACCESS.2024.3418900.

[3] K. Yu, K. Jin, and X. Deng, ‘Review of Deep Reinforcement Learning’, in 2022 IEEE 5th Advanced Information Management, Communicates, Electronic and Automation Control Conference (IMCEC), Dec. 2022, pp. 41–48. doi: 10.1109/IMCEC55388.2022.10020015.

[4] D.-H. Tran, N. Van Huynh, S. Kaada, V. N. Vo, E. Lagunas, and S. Chatzinotas, ‘Network Energy Saving for 6G and Beyond: A Deep Reinforcement Learning Approach’, in 2025 IEEE Wireless Communications and Networking Conference (WCNC), Mar. 2025, pp. 1–6. doi: 10.1109/WCNC61545.2025.10978758.

[5] M. M. Saeed, R. A. Saeed, E. S. Ali, R. A. Mokhtar, and O. O. Khalifa, ‘Algorithm for Resource Allocation and Computing Offloading in 6G Networks: Deep Reinforcement Learning-based’, in 2024 9th International Conference on Mechatronics Engineering (ICOM), Aug. 2024, pp. 188–193. doi: 10.1109/ICOM61675.2024.10652281.

[6] H. She, L. Yan, and Y. Guo, ‘Efficient End–Edge–Cloud Task Offloading in 6G Networks Based on Multiagent Deep Reinforcement Learning’, IEEE Internet Things J., vol. 11, no. 11, pp. 20260–20270, June 2024, doi: 10.1109/JIOT.2024.3372614.

[7] L. P. Qian, H. Zhang, Q. Wang, Y. Wu, and B. Lin, ‘Joint Multi-Domain Resource Allocation and Trajectory Optimization in UAV-Assisted Maritime IoT Networks’, IEEE Internet Things J., vol. 10, no. 1, pp. 539–552, Jan. 2023, doi: 10.1109/JIOT.2022.3201017.

[8] S. Bassoy, R. Behravesh, and J. Pujol-Roig, ‘SEEDRL: Smart Energy Efficiency Using Deep Reinforcement Learning for 6G Networks’, in 2023 IEEE Globecom Workshops (GC Wkshps), Dec. 2023, pp. 732–737. doi: 10.1109/GCWkshps58843.2023.10464558.

[9] M. Diamanti, G. Kapsalis, E. E. Tsiropoulou, and S. Papavassiliou, ‘Energy-Efficient Rate-Splitting Multiple Access: A Deep Reinforcement Learning-Based Framework’, IEEE Open J. Commun. Soc., vol. 4, pp. 2397–2409, 2023, doi: 10.1109/OJCOMS.2023.3322047.

[10] Y. Ju et al., ‘Deep Reinforcement Learning Based Joint Beam Allocation and Relay Selection in mmWave Vehicular Networks’, IEEE Trans. Commun., vol. 71, no. 4, pp. 1997–2012, Apr. 2023, doi: 10.1109/TCOMM.2023.3240754.

[11] J.-H. Lee, H. Seo, J. Park, M. Bennis, and Y.-C. Ko, ‘Learning Emergent Random-Access Protocol for LEO Satellite Networks’, IEEE Trans. Wirel. Commun., vol. 22, no. 1, pp. 257–269, Jan. 2023, doi: 10.1109/TWC.2022.3192365.

[12] H. Ju, S. Kim, Y. Kim, and B. Shim, ‘Energy-Efficient Ultra-Dense Network with Deep Reinforcement Learning’, IEEE Trans. Wirel. Commun., vol. 21, no. 8, pp. 6539–6552, Aug. 2022, doi: 10.1109/TWC.2022.3150425.

[13] H. Zhang, M. Huang, H. Zhou, X. Wang, N. Wang, and K. Long, ‘Capacity Maximization in RIS-UAV Networks: A DDQN-Based Trajectory and Phase Shift Optimization Approach’, IEEE Trans. Wirel. Commun., vol. 22, no. 4, pp. 2583–2591, Apr. 2023, doi: 10.1109/TWC.2022.3212830.

[14] H. Peng and L.-C. Wang, ‘Energy Harvesting Reconfigurable Intelligent Surface for UAV Based on Robust Deep Reinforcement Learning’, IEEE Trans. Wirel. Commun., vol. 22, no. 10, pp. 6826–6838, Oct. 2023, doi: 10.1109/TWC.2023.3245820.

[15] B. Mao, F. Tang, Y. Kawamoto, and N. Kato, ‘AI Models for Green Communications Towards 6G’, IEEE Commun. Surv. Tutor., vol. 24, no. 1, pp. 210–247, 2022, doi: 10.1109/COMST.2021.3130901.

[16] N. Capuano, G. Fenza, V. Loia, and C. Stanzione, ‘Explainable Artificial Intelligence in CyberSecurity: A Survey’, IEEE Access, vol. 10, pp. 93575–93600, 2022, doi: 10.1109/ACCESS.2022.3204171.

[17] J. J. Alcaraz, F. Losilla, A. Zanella, and M. Zorzi, ‘Model-Based Reinforcement Learning with Kernels for Resource Allocation in RAN Slices’, IEEE Trans. Wirel. Commun., vol. 22, no. 1, pp. 486–501, Jan. 2023, doi: 10.1109/TWC.2022.3195570.

[18] P. Zhang, Y. Xiao, Y. Li, X. Ge, G. Shi, and Y. Yang, ‘Toward Net-Zero Carbon Emissions in Network AI for 6G and Beyond’, IEEE Commun. Mag., vol. 62, no. 4, pp. 58–64, Apr. 2024, doi: 10.1109/MCOM.003.2300175.

[19] R. Kamran, S. Kiran, P. Jha, A. Karandikar’T, and P. Chaporkar, ‘Green 6G: Energy Awareness in Design’, in 2024 16th International Conference on COMmunication Systems & NETworkS (COMSNETS), Jan. 2024, pp. 1122–1125. doi: 10.1109/COMSNETS59351.2024.10427334.

[20] P. Liu, W. Yuan, J. Fu, Z. Jiang, H. Hayashi, and G. Neubig, ‘Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing’, ACM Comput. Surv., vol. 55, no. 9, pp. 1–35, Sept. 2023, doi: 10.1145/3560815.