A Developed Beyond 5G Massive Radio Access Networks Based On Artificial Intelligence Techniques

The main aims of fifth-generation (5G) are to enhance the signal, improve quality of service (QOS) and make mobile service available everywhere for any device. It is also expected to open up new use cases for many vertical industrial applications, such as Healthcare, Education, public transportation, medical care, Autonomous Vehicles, public safety, Smart Cities, agriculture, manufacturing, and so on. The number of users, traffic, and data rate are expected to rise quickly. In the next infrequent years, mobile users and vertical industries will need new ways to meet their needs. Redesigning the network architecture, or rebuilding the radio access network, is a good choice among the available options. This study used Long Short Term Memory (LSTM) with an Adam optimizer algorithm to predict the best channel quality indicators (CQI). In this LSTM, weight vectors are made in a way that is based on each other. The Adam algorithm is used to find the best values for these weights. The experimental result considers how accurate the forecast was and how well the inventory was. The results of experiments show that Recurrent Neural Network (RNN-LSTM) with an Adam algorithm works well and makes fewer mistakes than other methods. We conclude that the proposed work with the Adam algorithm works well for predicting the quality indicators of the channel (CQI).