5g network resource allocation management using Non Orthogonal Multiple Access based on machine learning

Non Orthogonal Multiple Access, or NOMA, is a multiple access scheme proposed for Future Radio Access (FRA). It is one of the many technologies that promise greater capacity gain and spectral efficiency than the present state of the art, and as such, is a candidate technology for 5G cellular networks. Each generation of cellular technology is usually characterized by a specific multiple access scheme. The wireless industry has seen technologies like Frequency Division Multiple Access (FDMA), Time Division Multiple Access (TDMA), Wideband Code Division Multiple Access (WCDMA) and Orthogonal Frequency Division Multiple Access (OFDMA) from the first to the fourth generation. One tool for examining the existence and development of such systems is the use of artificial intelligence systems Therefore, in this paper, we present an machine learning algorithm to improve resource allocation management that optimizes the number of scheduled users.

Keywords:

Bayesian Regularization Algorithm (BRA) , Mean Squared Error )MSE) , Multi-User Detection (MUD) , NOMA , Random Repetition Algorithm (RIA).