An Effective Cognitive Radio Network Based Improved Differential Evolution Optimization in Energy Harvesting Scenarios

Energy harvesting-based Device to Device (D2D) communication, powered by renewable energy sources, contributes to sustainable and eco-friendly communication systems. Developing a model for cognitive radio-based D2D communication in energy harvesting scenarios addresses the need for energy-efficient, reliable, and adaptive communication systems capable of operating in resource-constrained environments. This research faces major problems such as sub-optimal power allocation and sub-optimal channel allocation. In this paper, propose the use of the Improved Differential Evolution optimization algorithm to enhance the energy efficiency of the model and improve throughput performance. Our model achieves better performance compared to other state-of-the-art methods. Evaluate the model on two different metrics, namely energy consumption and throughput. The numerical validation of energy consumption involves 50 D2D nodes with 10 Joules (J), while throughput evaluation includes 50 D2D nodes with 320 bits per second (bps). The model can be compared to similar existing models such as the Power Control-Fuzzy Clustering Method (PC-FCM) and the Hybrid Intelligent Clustering Strategy (HICS).