Analysis of AI-Driven Modulation for Cognitive Cellular Networks : DNN Approach

Objective: analyze the modulation scheme that can intelligently select the appropriate modulation model for service conditions to obtain a high Signal to Noise Ratio, as well as throughput efficiency on wireless networks through the DNN approach. Method: this study uses simulations with the Python language, through AI-Driven on BPSK, QPSK, 16-QAM, and 64-QAM modulation, to determine the SNR and Quality of Service (QoS) produced, both through conventional approaches and Deep Neuro Network (DNN). Researh Finding: AI-Driven modulation used for Cognitive Cellular Networks (CCN), through Deep Neuro Network designed to intelligently classify and select the appropriate modulation model to be applied, shows significant improvement in throughput efficiency, QoS and has the ability to adapt to the environment in dynamic networks. Conclussion: AI-Driven using Deep Neuro Network is able to dynamically adapt to determine the selected modulation model, according to the user's environmental conditions, increase spectrum efficiency and throughput, and increase SNR which can automatically increase the efficiency of network usage.