Sungkyunkwan University conducted this study with the support of Accuver (XCAL-Solo III). 

They have proposed a self-attention-based deep learning model to predict uplink radio resource in 5G Dual Connectivity (5G DC). The model was trained on commercial 5G DC traffic data from three major carriers in South Korea and achieved an average prediction accuracy of 95.08% under various mobility and cell-load conditions.