Performance Analysis of Adaptive Beamforming in a MIMO-millimeter Wave
5G Heterogeneous Wireless Network using Machine Learning
Beamforming (BF) always guides to determine the quality of received
signal by an antenna array using Signal-to-Noise-Interference Ratio
(SINR) in cellular base stations. This paper will help in the
installation of 5G and 6G Millimeter-Wave (mm-Wave) heterogeneous
wireless networks. Here, adaptive BF is designed and being implemented
on the Machine Learning (ML) platform. The four ML methods having six BF
properties to estimate the SINR of Multiple-Input-Multiple-Output
(MIMO-mm-Wave) 5G wireless network are explored. The proposed algorithm
suppresses noise plus interference and can reduce the power consumption.
The python package pyArgus focusing on the BF and direction finding
algorithms has been used for 20,000 simulations. The BF features namely
noise variance, number of antenna elements, distance between antenna
elements, azimuth angular range of receiving array, elevation angular
range of receiving array and Direction of Arrival (DOA) of signal i.e.
incident angle of Signal-of-Interest (SOI) are used in predicting the
SINR. The 10-fold cross-validation experiment is performed to assess the
robustness of the best predictive method. By conducting the rigorous
simulations, it has been observed that Random Forest (RF) method
outperforms over the three other ML methods such as Tree model i.e.
rpart, Generalized Linear Model (glm) and Neural Network (nnet), which
does the prediction inexpensive and faster. The
performance analysis parameters’ result represents that the prediction
of Mean Absolute Error (MAE) by RF is lowest 70.73 in value, and its
Accuracy is maximum 86.40%, in value having the acceptable error on the
training-testing data set.