Deep Learning-Based MIMO and NOMA Energy Conservation and Sum Data Rate Management System

Future communication networks will require innovative ways to meet the rising expectations for huge connection, low latency, and great reliability. A promising approach to increase system throughput and energy competence is called MIMO-NOMA. It incorporates the NOMA concept into MIMO. However, quickly changing channel conditions and a highly complicated structure decreases performance of the system and limit its application. To address these restrictions, we present an Artificial Intelligence based structure for make the most of the ‘sum data’ proportion and power competence. To be more precise, we create a deep neural network (CDNN) for successful communication that has a number of convolutional layers as well as numerous hidden layers. The CDNN architecture overcomes the power challenge by utilizing the deep learning technique’s amazing representation.