Energy Optimization for MTN Green Communication Networks Using Artificial Neural Network

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.