Abstract
Millimeter-wave supplies an alternative frequency band of wide bandwidth to
better realize pillar technologies of enhanced mobile broadband (eMBB) and
ultra-reliable and lowlatency communication (uRLLC) for 5G - new radio (5G-NR).
When using mmWave frequency band, relay stations to assist the coverage of base
stations in radio access network (RAN) emerge as an attractive technique.
However, relay selection to result in the strongest link becomes the critical
technology to facilitate RAN using mmWave. A alternative approach toward relay
selection is to take advantage of existing operating data and apply appropriate
artificial neural networks (ANN) and deep learning algorithms to alleviate
severe fading in mmWave band. In this paper, we apply classification techniques
using ANN with multilayer perception to predict the path loss of multiple
transmitted links and base on a certain loss level, and thus execute effective
relay selection, which also recommends the handover to an appropriate path. ANN
with multilayer perceptions are compared with other ML algorithms to
demonstrate the effectiveness for relay selection in 5G-NR.