2021/08/01 by Anu T S, S, Anu T, Tara Raveendran +1
Engineering · #Antenna Design and Optimization #FOS: Computer and information sciences #FOS: Electrical engineering #Indoor and Outdoor Localization Technologies #Machine Learning (cs.LG) #Millimeter-Wave Propagation and Modeling #Signal Processing (eess.SP) #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.2108.00367
openalex publication_date 2021/08/01 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Non-Orthogonal Multiple Access (NOMA) schemes are being actively explored to address some of the major challenges in 5th Generation (5G) Wireless communications. Channel estimation is exceptionally challenging in scenarios where NOMA schemes are integrated with millimeter wave (mmWave) massive multiple-input multiple-output (MIMO) systems. An accurate estimation of the channel is essential in exploiting the benefits of the pairing of the duo-NOMA and mmWave. This paper proposes a convolutional neural network (CNN) based approach to estimate the channel for NOMA based millimeter wave (mmWave) massive multiple-input multiple-output (MIMO) systems built on a hybrid architecture. Initially, users are grouped into different clusters based on their channel gains and beamforming technique is performed to maximize the signal in the direction of desired cluster. A coarse estimation of the channel is first made from the received signal and this estimate is given as the input to CNN to fine estimate the channel coefficients. Numerical illustrations show that the proposed method outperforms least square (LS) estimate, minimum mean square error (MMSE) estimate and are close to the Cramer-Rao Bound (CRB).