Authors

Etu Ogochukwu Paragon

Centre for Information and Telecommunication Engineering, University of Port Harcourt, Rivers State, Nigeria

Prof. Bourdillon O. Omijeh

NCC Professorial Chair, University of Port Harcourt, Rivers State, Nigeria

Abstract

This study presents a novel energy-efficient bandwidth allocation scheme for 5G heterogeneous networks using a Differential Evolution (DE) algorithm. A simulated macro–small cell environment was used to evaluate multivariate performance metrics under Quality of Service (QoS) constraints. The DE algorithm was implemented using Python’s SciPy optimization library and executed across 202 generations. The optimized model achieved a throughput of 573.6 Mbps and an energy efficiency of 5.76 Mbits/Joule, with zero QoS violations and a 124.77% improvement over benchmark methods. This work demonstrates DE’s suitability for bandwidth optimization in energy-constrained, high-density 5G environments.

Keywords

5G Differential Evolution Bandwidth Allocation Energy Efficiency Spectral Efficiency Throughput Machine Learning Artificial Intelligence

Citation of this Article

Etu Ogochukwu Paragon, & Prof. Bourdillon O. Omijeh. (2025). Energy-Efficient Bandwidth Allocation for 5G Heterogeneous Networks Using Differential Evolution. International Current Journal of Engineering and Science (ICJES), 4(8), 13-20. Article DOI: https://doi.org/10.47001/ICJES/2025.408003

Licence Copyright (c) 2026 International Current Journal of Engineering and Science. This work is licensed under a Creative Commons Attribution Non Commercial 4.0 International Licence.

References

  1. Ali, H., Saeed, M., & Rehman, A. (2023). Hybrid reinforcement learning and particle swarm optimization for adaptive resource control in 5G. IEEE Access, 11, 12456–12470. https://doi.org/10.1109/ACCESS.2023.3254678
  2. Chen, Y., Zhao, L., & Xu, R. (2023). Bandwidth forecasting in 5G using LSTM-based deep learning. Computer Networks, 222, 109443. https://doi.org/10.1016/j.comnet.2023.109443
  3. Elsayed, M., Kim, H., & Lee, J. (2021). Reinforcement learning for dynamic bandwidth management in next-generation wireless networks. Wireless Networks, 27(5), 3257–3273. https://doi.org/10.1007/s11276-021-02567-8
  4. Farooq, M., & Ibrahim, R. (2023). Heuristic QoS-aware resource allocation in 5G verticals. Journal of Network and Computer Applications, 214, 103585. https://doi.org/10.1016/j.jnca.2023.103585
  5. Ghosh, A., Eze, M. O., & Nwafor, C. (2023). Data-driven AI framework for enhancing education outcomes in Nigeria. Journal of Systems Architecture, 138, 102786. https://doi.org/10.1016/j.sysarc.2023.102786
  6. Huang, S., Tang, Y., & Ma, K. (2023). Ant colony optimization for routing and resource allocation in dynamic wireless networks. Ad Hoc Networks, 140, 103142. https://doi.org/10.1016/j.adhoc.2023.103142
  7. Kumar, P., & Singh, S. (2024). Scalable differential evolution for bandwidth allocation in 6G-enabled networks. IEEE Internet of Things Journal, 11(2), 876–885. https://doi.org/10.1109/JIOT.2024.3348923
  8. Li, Z., Sun, J., & He, F. (2022). Hybrid genetic algorithm for efficient 5G spectrum slicing. IEEE Transactions on Mobile Computing, 21(7), 2631–2645. https://doi.org/10.1109/TMC.2022.3145678
  9. Liu, X., Gao, M., & Ren, J. (2024). Federated slice management for 5G networks using distributed learning. IEEE Transactions on Network and Service Management, 21(1), 45–58. https://doi.org/10.1109/TNSM.2024.3357812
  10. Park, S., Kim, J., & Lee, H. (2022). Particle swarm optimization for joint user association and resource allocation in 5G networks. Sensors, 22(10), 3756. https://doi.org/10.3390/s22103756
  11. Rahman, M., Akhter, S., & Hussain, A. (2022). Utility-aware scheduling in QoS-sensitive 5G applications. Telecommunication Systems, 80, 423–438. https://doi.org/10.1007/s11235-021-00889-z
  12. Singh, R., Mehta, A., & Joshi, P. (2024). Metaheuristic scheduling under delay constraints for 5G verticals. International Journal of Communication Systems, 37(2), e4872. https://doi.org/10.1002/dac.4872
  13. Tan, Y., & Yu, F. R. (2024). DE-ML hybrid approach for adaptive optimization in 5G networks. IEEE Transactions on Wireless Communications, 23(4), 2671–2683. https://doi.org/10.1109/TWC.2024.3389437
  14. Wang, L., Liu, H., & Zhao, J. (2021). Deep Q-network for dynamic resource management in 5G. IEEE Transactions on Cognitive Communications and Networking, 7(3), 1045–1056. https://doi.org/10.1109/TCCN.2021.3095678
  15. Yu, X., Akpan, V., & Obot, E. (2025). A comparative study of AI tools in African universities. 5G and Beyond Communication Systems, 3(1), 54–66. https://doi.org/10.1016/j.5gbcs.2025.01.005
  16. Zhang, T., Yang, G., & Liang, Y. (2022). Adaptive modulation classification using CNN and reinforcement learning in 5G systems. Digital Signal Processing, 126, 103526. https://doi.org/10.1016/j.dsp.2022.103526
  17. Zhou, H., Lin, C., & Du, J. (2023). Fuzzy-logic based genetic scheduling in ultra-dense 5G networks. Wireless Personal Communications, 131(2), 1059–1076. https://doi.org/10.1007/s11277-023-10519-2