Energy-Efficient Network Slice Management and Power Optimization in 5G Systems
Abstract
Energy consumption in 5G networks has emerged as a critical challenge due to the rapid proliferation of connected devices, diverse service demands, and the increasing complexity of network infrastructure. This article addresses energy-efficient network slice management through machine learning-based power optimization strategies. We propose an integrated framework combining LSTM-based power consumption forecasting, attention-mechanism networks for dynamic power allocation, and multi-objective reinforcement learning for slice-level energy management. The approach balances energy efficiency with quality-of-service (QoS) requirements across heterogeneous network slices serving enhanced mobile broadband (eMBB), massive machine-type communications (mMTC), and ultra-reliable low-latency communications (URLLC) services. Extensive simulations demonstrate 18-25% reduction in power consumption while maintaining strict SLA compliance, making the approach viable for sustainable 5G deployment.
References
[[1] Karanasios, S., Robertson, S., & Allen, D. (2023). The energy footprint of 5G technologies: Progress and future perspectives. IEEE Communications Magazine, 61(3), 112-120. https://doi.org/10.1109/MCOM.2023.3145678
Zhang, H., Li, Z., Wang, R., & Zhou, M. (2022). Energy-efficient resource management in 5G mobile networks. IEEE Transactions on Wireless Communications, 21(4), 2645-2657. https://doi.org/10.1109/TWC.2021.3118956
Chen, Q., Zhao, H., Wang, Y., & Han, L. (2023). Network slicing for multi-service 5G networks: Architecture, algorithms, and performance. ACM Computing Surveys, 56(2), 1-38. https://doi.org/10.1145/3545925
López-Pérez, D., López-García, Á., Ramos-Cantos, A., & Valcarce, A. (2022). Energy-efficient power control in heterogeneous networks: A machine learning approach. IEEE Access, 10, 45123-45138. https://doi.org/10.1109/ACCESS.2022.3170832
Wang, L., Liu, Y., Song, T., Pan, Y., & Chen, Z. (2023). Deep learning for wireless power management: From forecasting to optimization. IEEE Journal on Selected Areas in Communications, 41(3), 756-769. https://doi.org/10.1109/JSAC.2022.3219646
Hao, Z., Qiao, Z., Dang, X., Zhang, D., Duan, Y., & Li, N. (2023). Attention-based reinforcement learning for dynamic resource allocation in mobile networks. IEEE Transactions on Network and Service Management, 20(1), 542-556. https://doi.org/10.1109/TNSM.2023.3245801
Sun, J., Zhao, Y., Wang, Y., Li, N., Zhang, H., & Sun, X. (2022). Multi-objective deep reinforcement learning for spectrum resource allocation. IEEE Transactions on Mobile Computing, 21(8), 2890-2905. https://doi.org/10.1109/TMC.2021.3087654
European Commission. (2023). Towards green and sustainable 6G networks. Digital Europe Programme, Report No. DEP-2023-456. Retrieved from https://digital-strategy.ec.europa.eu/reports/6g-sustainability
Mukherjee, A., Panja, A. K., & Dey, N. (2021). Renewable energy integration in cellular networks: Architectures and algorithms. Renewable and Sustainable Energy Reviews, 142, 110834. https://doi.org/10.1016/j.rser.2021.110834
Kasiviswanathan, U., Poddar, S., Kumar, C., Jit, S., & Sharma, N. (2022). Federated learning for distributed power management in multi-operator networks. IEEE Transactions on Wireless Communications, 21(5), 3445-3460. https://doi.org/10.1109/TWC.2021.3122456
Downloads
Published
How to Cite
License
Copyright (c) 2025 Journal of Reproducible Research
This work is licensed under a Creative Commons Attribution 4.0 International License.
Copyright of the article belongs to Journal of Reproducible Research (JRR) once the paper is ACCEPTED for publication. Author(s) agrees to this terms, during submission.
