Deep Learning and Smart Antennas for Beamforming Strategies

With the advent of the 5G and future 6G, base stations will be used as station controllers. The antenna systems are networked and equipped with a processor to optimize the detection of signal arrival, beamforming, and computing time. The present work aims to improve the antenna radiation pattern by using neural networks and CDRs (Call Detail Records) according to the spatial occupation of the area by the users. It focuses on the computation time of synthesis algorithms by Deep learning and proposes an optimal management strategy. The tests carried out show that Despite the diversity of the quality of the results provided, the computation times remain comparable for the classical DoA estimation methods, the slowest being the PRONY approach (linear prediction). The neural network approach has the advantage of being a global optimum search technique requiring the shortest computational time, which is about 10 times the time required for a local optimum approach. Neural network and spectral methods reduce the influence of noise on communication to zero. It has proposed a new approach based on mathematical modeling to exploit blocked TRX to cancel the radiation on this channel.