Deep Learning aided SIC for Wavelet-based Massive MIMO-NOMA
In this study, a deep neural network (DNN) for a massive multiple-input-multiple-output (mMIMO) nonorthogonal multiple access (NOMA) system’s channel estimation and detection is presented. The proposed network applies deep learning (DL) to a discrete wavelet transform (DWT) based orthogonal frequency-division-multiplexing (OFDM) to reduce the noise and inter-channel interference (ICI) while maintaining compatibility with the existing networks. The transmission overhead is reduced because the presented network is trained to estimate and detect symbols with and without pilot signals.
The results of this study demonstrate that our provided DL-based successive interference cancellation (SIC) method performs better than the conventional SIC-based signal detection in the mMIMONOMA network. The suggested wavelet-based mMIMO-NOMA is also compared to the traditional fast-Fourier-transform (FFT) based mMIMO-NOMA, particularly in terms of symbol error rate (SER).
National Research Foundation of Korea (NRF)
Email Address of Submitting Authormuneeb.email@example.com
ORCID of Submitting Author0000-0002-7681-8699
Submitting Author's InstitutionKumoh National Institute of Technology
Submitting Author's Country
- Korea, Republic of (South Korea)