A Review on The Current Research Status of Base Station Sleep Strategies Using Deep Reinforcement Learning

Authors

  • Pushen Chen

DOI:

https://doi.org/10.54097/qzc02716

Keywords:

Deep Reinforcement Learning; Base Station Sleep; Energy Efficiency Optimization; Deep Q Network; Ultra-Dense Network.

Abstract

This paper presents a comprehensive review of the current research status and application advancements of deep reinforcement learning (DRL) in base station (BS) sleep control. With the ultra-dense deployment of 5G/6G networks, the energy consumption of BSs has become a critical issue, making dynamic sleep control a key technology for improving energy efficiency (EE). This work systematically analyzes core DRL-based approaches for BS sleep strategies, including DQN, PPO, DDPG, and others, as well as their trade-off mechanisms for multi-objective optimization involving EE, spectral efficiency (SE), and quality of service (QoS). Furthermore, it explores joint optimization schemes integrating emerging technologies such as renewable energy, cell zooming, and reconfigurable intelligent surfaces (RIS). A tripartite taxonomy is proposed, categorizing existing methods into value-based, policy gradient-based, and hybrid algorithms. Representative studies are summarized, highlighting the advantages and challenges of current DRL techniques in BS sleep control.

Downloads

Download data is not yet available.

References

[1] Q. Chen, X. Bao, S. Chen and J. Zhao, Base station power control strategy in ultra-dense networks via deep reinforcement learning, Physical Communication, Volume 71, Page 10265, August 2025

[2] Zeng Dezhe, Li Yuopeng, Zhao Yuyang, et al. A High-Efficiency Base Station Dynamic Scheduling Method Based on Reinforcement Learning [J]. Computer Science,2021,48(11):363-371.

[3] Yang Fuyu, Zhao Dong. Base Station Sleep Control Algorithm Based on Deep Reinforcement Learning [J]. High-Quality Papers from China Science and Technology Paper Online,2023,16(02):170-178.

[4] J. Liu, B. Krishnamachari, S. Zhou and Z. Niu, DeepNap: Data-Driven Base Station Sleeping Operations Through Deep Reinforcement Learning, IEEE Internet Things J., Volume 5, Issue 6, Page 4273-4282, December 2018

[5] S. Sun, C. Huang, G. Chen, P. Xiaoand R. Tafazolli, Deep Learning-Based Traffic-Aware Base Station Sleep Mode and Cell Zooming Strategy in RIS-Aided Multi-Cell Networks, IEEE Trans. Cogn. Commun. Netw., page1-1, 2024

[6] J. Gan, H. Kou, G. Yang, H. Zhang, Z. Cao andW. Xu, Joint Sleep Control and Energy Sharing Strategy with Deep Reinforcement Learning in Green Ultra-Dense Networks, IEEE Trans. on Green Commun. Netw., page 1-1, 2025

[7] Y. M. Park, S. S. Hassan and C. S. Hong, "Maximizing Throughput of Aerial Base Stations via Resources-based Multi-Agent Proximal Policy Optimization: A Deep Reinforcement Learning Approach," 2022 23rd Asia-Pacific Network Operations and Management Symposium (APNOMS), Takamatsu, Japan, 2022, pp. 1-4

[8] Y. Bo, K. Kang, W. Li, G. Pan and M. Wang, "A Low-Altitude Network Base Station Planning Model Based on PPO Algorithm," 2024 IEEE 10th International Symposium on Microwave, Antenna, Propagation and EMC Technologies for Wireless Communications (MAPE), Guangzhou, China, 2024, pp. 1-4

[9] Q. Wu, X. Chen, Z. Zhou, L. Chen and J. Zhang, Deep Reinforcement Learning With Spatio-Temporal Traffic Forecasting for Data-Driven Base Station Sleep Control, IEEE/ACM Trans. Networking, Volume29, Issue 2, Page 935-948, April 2021

[10] G. Saranya and E. Sasikala, "A Deep Reinforcement Learning based policy gradient for Energy Consumption in Edge Computing," 2022 International Conference on Computer, Power and Communications (ICCPC), Chennai, India, 2022, pp. 71-76

[11] J. Song, B. Zhang and J. Lia, "Deep Reinforcement Learning Empowered Particle Swarm Optimization for Aerial Base Station Deployment," 2023 IEEE Applied Sensing Conference (APSCON), Bengaluru, India, 2023, pp. 1-3

[12] L. Ma, X. Zhang, J. Sun, W. Zhang and C. -X. Wang, "Joint Optimization of Reconfigurable Intelligent Surfaces and Base Station Beamforming in MISO System Based on Deep Reinforcement Learning," 2023 IEEE 97th Vehicular Technology Conference (VTC2023-Spring), Florence, Italy, 2023, pp. 1-5

[13] Lee, H., Eom, C., & Lee, C. (2023). QoS-aware UAV-BS deployment optimization based on reinforcement learning. 2023 International Conference on Electronics, Information, and Communication (ICEIC) (pp. 1-4). IEEE.

Downloads

Published

13-11-2025

Issue

Section

Articles