A Comparative Study of Deep Leaning-Aided Relay Selection Protocols in Cooperative Communication

Abstract

Deep learning (DL) is an emerging topic that has found its place in various applications due to its many advantages, such as providing good performance and reducing complexity. In this paper, we used different DL algorithms for channel coefficients estimation in a cooperative communication by performing maximum likelihood estimation (MLE) to combine different copies of transmitted signal over a binary phase-shift keying (BPSK) modulation in a Rayleigh fading communication channel. We have proposed three different relay selection protocols in which, the first one is SNR-based; the SNRs of the transmission lines between nodes are calculated, and the relay with maximum SNR is selected among the relays. The second relay selection protocol is threshold-based; average SNRs have been obtained for all transmission links, and the links exceeding the average SNR join in the collaboration. The third proposed relay selection protocol is that all relays in the network participate in cooperation, which performed better performance metrics in terms of bit error rate (BER) and outage analysis. From our simulation results, DL-based forecasting achieved good performance for channel coefficients estimation in the proposed different relay selection protocols for the Decode and Forward (DF) relaying system.