The Reinforcement Learning based Interference Whitening Scheme for 5G

Abstract

To achieve high spectral efficiency, a modern cellular network such as LTE or 5G New Radio (NR) aims to operate with full frequency reuse. This deployment will significantly increase the level of Co-Channel Interference (CCI) for cell-edge User Equipments (UEs), and the CCI has become a major throughput-limiting factor. Thus, the suppression of CCI in the 5G network is the most important feature to increase downlink throughput. In order to mitigate CCI, Interference Whitening (IW) is an effective low-complexity linear method to suppress colored interference in a MIMO-OFDM system. However, conventional IW can degrade the performance when the noise-dominant environment due to limited samples, e.g., DMRS (De-Modulation Reference Signal). To address that, we propose a Reinforcement Learning based Interference Whitening (RL-IW) that adaptively controls the IW mode by learning algorithm. The experimental results show that RL-IW has performance gain in terms of both BLER (Block Error Rate) and downlink throughput than conventional IW.