Home / Current Issue / Paper 1723103
Energy Optimization for MTN Green Communication Networks Using Artificial Neural Network
Subject area: Science,Engineering and Technology · Area of research: Energy Optimization
Abstract
Artificial Neural Networks (ANNs) have emerged as an effective approach to improve energy efficiency in cellular communication networks. Cellular base stations account for over 70% of the energy consumed in cellular communication networks. Reducing the power consumed by these stations while maintaining Quality of Service (QoS) is needed to ensuring the sustainability of mobile communication networks. An ANN-based model was created to optimize the energy consumption of MTN green communication networks. The model was created using MATLAB/Simulink that would predict the power demand of cellular base stations based on several input variables. The model adapts base station operation to use energy optimally while ensuring continuous network coverage and QoS. To accomplish this, the model is built using base station operating data from MTN, Nigeria, which was trained, validated and evaluated under different traffic load conditions. Performance was compared with the conventional base station operation and Model Predictive Control (MPC) approach. Simulation results show that the conventional system consumes an average power of 2955 W while the ANN model achieves a reduction to 2847 W, representing 3.65% energy savings. Also, the MPC approach achieved a further reduction to 2747 W representing 7.04%. Although the MPC achieved the least energy consumption, the ANN has a good prediction accuracy coupled with adaptive learning which makes it have low computational complexity. The study concludes that ANN is a reliable method for improving the efficiency of energy usage within the network, reducing the amount of greenhouse gas emissions that are released into the atmosphere, reducing the costs of operating the network and improving the overall sustainability of green communication networks.
Keywords
artificial neural network, base station, energy optimization, green communication network, mtn, quality of service. renewable energy.
References
[1] Bonthu, R. K., R. P. Aguilera, H. Pham, M. D. Phung and Q. P. Ha., 2019. “Energy Cost Optimization in Microgrids Using Model Predictive Control and Mixed Integer Linear Programming,” IEEE International Conference on Industrial Technology (ICIT), Melbourne, VIC, Australia, pp. 1113-1118. IEEE
[2] Binzagr, F., Prabuwono, A. S., Alaoui, M. K., 2024. Energy efficient multi-carrier NOMA and power controlled resource allocation for B5G/6G networks. Wireless Netwotk.
[3] Chang, Y.-T., et al., 2012. Optimization the Initial Weights of Artificial Neural Networks via Genetic Algorithm Applied to Hip Bone Fracture Prediction. Advances in Fuzzy Systems, p. 9. Wiley
[4] Chen, R., Li, L., Xue, K., Zhang, C., Pan, M., and Fang, Y., 2022. Energy efficient federated learning over heterogeneous mobile devices via joint design of weight quantization and wireless transmission. IEEE Transactions on Mobile Computing, 22(12), pp. 7451-7465.
[5] Chung, M. H., et al., 2017. Application of artificial neural networks for determining energy-efficient operating set-points of the VRF cooling system. Building and Environment, 125, p. 77-87. ScienceDirect
[6] Elghamrawy, S., Ismail, A. H., and Hassanien, A. E., 2024. Energy consumption optimization in green cognitive radio networks based on collaborative spectrum sensing. EURASIP Journal on Wireless Communications and Networking, 2024(1), p. 78. Springer
[7] Hossain, M. S., Jahid, A., Ziaul Islam, K., Alsharif, M. H., and Rahman, M. F., 2020. Multi-objective optimum design of hybrid renewable energy system for sustainable energy supply to a green cellular networks. Sustainability, 12(9), p. 3536. MDPI
[8] Ozturk, M., Abubakar, A. I., Nadas, J. P. B., Rais, R. N. B., Hussain, S., and Imran, M. A., 2021. Energy optimization in ultra-dense radio access networks via traffic-aware cell switching. IEEE Transactions on Green Communications and Networking, 5(2), pp. 832-845. IEEE
[9] Wang, L., E. W. M. Lee, and R. K. K. Yuen, 2018. Novel dynamic forecasting model for building cooling loads combining an artificial neural network and an ensemble approach. Applied Energy, 228, p. 1740-1753. ScienceDirect
How to cite this paper
@article{1723103,
author = {Onwuha, U. H., Ene, P. C., Onuigbo, C. M},
title = {Energy Optimization for MTN Green Communication Networks Using Artificial Neural Network},
journal = {Iconic Research And Engineering Journals},
year = {2026},
volume = {10},
number = {3},
pages = {1993-2006},
issn = {2456-8880},
url = {https://www.irejournals.com/formatedpaper/1723103.pdf},
abstract = {Artificial Neural Networks (ANNs) have emerged as an effective approach to improve energy efficiency in cellular communication networks. Cellular base stations account for over 70% of the energy consumed in cellular communication networks. Reducing the power consumed by these stations while maintaining Quality of Service (QoS) is needed to ensuring the sustainability of mobile communication networks. An ANN-based model was created to optimize the energy consumption of MTN green communication networks. The model was created using MATLAB/Simulink that would predict the power demand of cellular base stations based on several input variables. The model adapts base station operation to use energy optimally while ensuring continuous network coverage and QoS. To accomplish this, the model is built using base station operating data from MTN, Nigeria, which was trained, validated and evaluated under different traffic load conditions. Performance was compared with the conventional base station operation and Model Predictive Control (MPC) approach. Simulation results show that the conventional system consumes an average power of 2955 W while the ANN model achieves a reduction to 2847 W, representing 3.65% energy savings. Also, the MPC approach achieved a further reduction to 2747 W representing 7.04%. Although the MPC achieved the least energy consumption, the ANN has a good prediction accuracy coupled with adaptive learning which makes it have low computational complexity. The study concludes that ANN is a reliable method for improving the efficiency of energy usage within the network, reducing the amount of greenhouse gas emissions that are released into the atmosphere, reducing the costs of operating the network and improving the overall sustainability of green communication networks.},
keywords = {artificial neural network, base station, energy optimization, green communication network, mtn, quality of service. renewable energy.},
month = {September},
}