Implementation of the deep learning method for signal detection in massive-MIMO-NOMA systems.

The deep learning method (DLM) is one way to fix issues in optical nonorthogonal multiple access (O-NOMA) systems that are caused by signals that overlap and interfere with each other. NOMA increases the optical framework's spectrum efficiency, allowing several users to share the same time-frequency resources. However, NOMA-DLM-based detection's complicated interference patterns and variable channel conditions are challenging for conventional detection methods to manage. By utilizing deep neural networks' advantages, these methods are able to overcome these challenges and improve detection performance. An overview of the main features and advantages of DLM detection in massive multiple input and output (M-MIMO) O-NOMA systems is given in this article. It describes the essential elements, such as the training procedure and the network design. In order to process the sent symbols or decode data streams, DLM networks are built to process the incoming signal, power allocation coefficients, and extra information. Gradient descent optimization is used to update the network parameters iteratively while training the network, and a diverse and representative dataset is created. Additionally, the challenges of detecting deep learning in O-NOMA systems are examined. It recognizes that in order to get the best results, significant computational resources, a large amount of training data, and careful model design are required. It looks at and compares the 16 × 16, 32 × 32, and 64 × 64 M-MIMO-NOMA models in terms of bit error rate (BER), complexity, and power spectral density (PSD). The suggested DLM algorithms have been demonstrated to perform better than traditional methods by achieving an excellent BER of 10-3 at 4.1 dB and PSD (-2500) performance with low complexity.