ELMx-based Channel Estimation for Massive MIMO Systems
Chittapon Keawin, Peerapong Uthansakul, Apinya Deekaikam · 2021
The channel estimation of massive MIMO systems is one of the recent developments in wireless communication technology. The more accurate channel is estimated, the higher performance is achieved. In this paper, the use of machine learning applied to channel estimation is studied. Also, the proposed channel estimations based on Extreme Learning Machine (ELM) family are implemented for massive MIMO systems. These estimations include ELM, Regularized Extreme Learning Machine (RELM) and Outlier Robust Extreme Learning Machine (ORELM). Then, the comparison between two legacy channel estimations using Least Squares (LS) and Minimum Mean Squares Error (MMSE) is presented. The simulation results reveal that the proposed methods significantly overcome LS and MMSE.