Selection of Optimum Transmit Antenna Based on Convolutional Neural Networks in Mobile Fading Channels

Abstract

This paper proposes a new technique for selecting optimal transmit antennas using convolutional neural network (CNN) in mobile communication environments. The communication system considered in this paper has multiple antennas and time-division duplexing (TDD) mode. In a receiver mode, it utilizes all the antennas but uses only one antenna in a transmitter mode. The proposed method is an optimal antenna selection technique based on CNN for future transmission time. The input of the CNN the signal to ratios (SNRS) for the past received signals. Conventional method selects the optimal antenna based on the average of the past received SNRs or the most recently received SNR. We compare the proposed method with two conventional methods through computer simulation. According to the simulation results, by changing the mobile speed and the probability (or frequency) of receiving, the proposed CNN method has the highest accuracy in wideband signals while the convolutional method using the recent received SNR has the highest accuracy in narrowband signals.