The survey of AI-Empowered Energy Efficiency Optimization in Ultra-Dense 6G Edge Networks

Authors

  • Guilin Zhang Nanjing University of Posts and Telecommunications, Nanjing, 210023, China

DOI:

https://doi.org/10.54691/b3avj853

Keywords:

6G network; UDN; Edge computing; AI; deep reinforcement learning; Green communication.

Abstract

This paper conducts a comprehensive investigation into the energy efficiency optimization driven by artificial intelligence in ultra-dense 6G edge networks, providing reference methods for key challenges such as high energy consumption, dynamic resource management, and multi-objective trade-offs. Traditional methods often lack adaptability and real-time performance, prompting the exploration of advanced artificial intelligence technologies, including deep reinforcement learning (DRL), federated learning (FL), graph neural networks (GNN), and long short-term memory (LSTM) networks. Although challenges such as training complexity, data dependence, and device heterogeneity still exist, these methods show great potential in reducing energy consumption while maintaining service quality. We propose a closed-loop framework that integrates DRL for real-time control, FL for privacy-preserving distributed optimization, GNN for topology-aware resource allocation, and LSTM for time-flow prediction. Additionally, we have identified key future research directions, such as algorithm lightweighting, multi-objective dynamic optimization, cross-domain integration, and standardization efforts. By combining the most advanced artificial intelligence technologies with emerging 6G requirements, this work provides a roadmap for achieving sustainable, intelligent, and energy-efficient 6G networks, ultimately advancing the global green communication goal.

Downloads

Download data is not yet available.

References

[1] Hossain, Mohammad et al., ”AI in 6G: Energy-Efficient Distributed Machine Learning for Multilayer Heterogeneous Networks,” IEEE Network., vol. 36, no. 6, 2022, pp. 84-91.

[2] Sun Yingying et al., ”Energy-Efficient Task Offloading Based on Differential Evolution in Edge Computing System with Energy Harvesting,” IEEE Access., vol. 9, 2021, pp. 16383-16391.

[3] Chopra, Garima ,”An Efficient Base Station Sleeping Configuration for Ultra-dense Networks,” IEEE., 2023 International Conference on Emerging Smart Computing and Informatics (ESCI), 2023, pp. 1-5.

[4] Mahmoud, Haitham et al., ”A Comprehensive Review of Generative AI Applications in 6G,” IEEE., 2024 6th Novel Intelligent and Leading Emerging Sciences Conference (NILES), 2024, pp. 593-596.

[5] Zhang, Tiankui et al., ”Energy Efficiency of Base Station Deployment in Ultra Dense HetNets: A Stochastic Geometry Analysis,” IEEE Wireless Communications Letters., vol. 5, no. 2, 2016, pp. 184-187.

[6] Lee, Hunmin et al., “FedAssist: Federated Learning in AI-Powered Prosthetics for Sustainable and Collaborative Learning,” 2024 46th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), IEEE, 2024, pp. 1-5.

[7] Ke, yin, “Bipartite Graph based Edge Server Placement Algorithm in Mobile Edge Computing,” 2021 International Conference on Electronic Information Engineering and Computer Science (EIECS), IEEE, 2021, pp. 493-496.

[8] Li, Haiyuan et al., “Towards Practical Operation of Deep Reinforcement Learning Agents in Real-World Network Management at Open RAN Edges,” IEEE Communications Magazine., 2025, pp. 1-7.

[9] Yang, Zhaohui et al., “Federated Learning for 6G: Applications, Challenges, and Opportunities,” Engineering., vol. 8, 2022, pp. 33-41.

[10] Zhou, Yuhao et al., “Federated CINN Clustering for Accurate Clustered Federated Learning,” ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), IEEE, 2024, pp. 5590-5594.

[11] Awasthi, A. K. et al., “GNN Model Based on Node Classification Forecasting in Social Network,” 2023 International Conference on Artificial Intelligence and Smart Communication (AISC), IEEE, 2023, pp. 1039-1043.

[12] Jiao, Licheng et al., “Advanced Deep Learning Models for 6G: Overview, Opportunities, and Challenges,” IEEE Access., vol. 12, 2024, pp. 133245-133314.

[13] Yu, Peng et al., “Digital Twin Driven Service Self-Healing with Graph Neural Networks in 6G Edge Networks,” IEEE Journal on Selected Areas in Communications., vol. 41, no. 11, 2023, pp. 3607-3623.

[14] Huang, Yunxue et al., ”A GNN-Enabled Multipath Routing Algorithm for Spatial-Temporal Varying LEO Satellite Networks,” IEEE Transactions on Vehicular Technology., vol. 73, no. 5, 2024, pp. 5454-5468.

[15] Akandeh, Atra and Salem, Fathi M., “Slim LSTM NETWORKS: LSTM_6 and LSTM_C6,”2019 IEEE 62nd International Midwest Symposium on Circuits and Systems (MWSCAS), IEEE, 2019, pp. 630-633.

[16] Nguyen, Chi et al., “Channel Estimation Using CNN-LSTM in RIS-NOMA Assisted 6G Network,” IEEE Transactions on Machine Learning in Communications and Networking., vol. 1, 2023, pp. 43-60.

[17] Murshed, Rafid Umayer et al., “A CNN-LSTM-Based Fusion Separation Deep Neural Network for 6G Ultra-Massive MIMO Hybrid Beamforming,” IEEE Access., vol. 11, 2023, pp. 38614-38630.

[18] Huang Xiaoyan et al., “Collaborative Machine Learning for Energy-Efficient Edge Networks in 6G,” IEEE Network., vol. 35, no. 6, 2021, pp. 12-19.

[19] Xie, Hao and Li, Dong, “Number Configuration for RIS-Aided Systems: Opportunities and Challenges,” IEEE Internet of Things Journal., vol. 12, no. 6, 2025, pp. 6396-6417.

Downloads

Published

2025-12-05

Issue

Section

Articles