GFDM Transceiver Based on Ann Channel Estimation

Abstract

Generalized frequency division multiplexing (GFDM) is one of the candidate waveforms beyond 5G for wireless communication. Channel estimation is challenging in wireless transmission because of inherent interference. It is based on a pilot signal that uses Least Square (LS) and Normalized Least Mean Square (NLMS) to perform the estimation. This paper used the Artificial Neural Network (ANN) as a channel estimation method, considered a novel estimation process for the GFDM transceiver. The channel estimation based on ANN depends on the data set generated from LS estimation, which considers the proposed method is optimized to LS based on the backpropagation neural network. The ANN algorithm considered a fitness function to estimate the channel. Levenberg-Marquardt backpropagation (LM), Bayesian Regularization backpropagation (BR), and Scaled Conjugate Gradient backpropagation (SCG) training methods training by using the Matlab toolbox used to perform the estimation. BR training method gives the best performance than LS and other training methods at 22 neurons in hidden layers, which at 20dB give BER = 0.0369 that enhanced over LS by 0.08.

Advanced lifting wavelet transform and V‐degree polynomial‐based channel estimation in MIMO‐GFDM

“…Some conventional methods regarding MIMO-GFDM communication are: Ali and Hreshee [8] introduced a deep learning-based channel estimation for MIMO-GFDM using an artificial neural network (ANN). In this study, three various learning strategies, scaled conjugate gradient, Bayesian regularization, and Levenberg-Marquardt method, were utilized for enhancing the channel detection accuracy.…”

“…In general, there are several 5G communication contenders. Some of these include generalized frequency division multiplexing (GFDM), filtered orthogonal frequency division multiplexing (f-OFDM), non-orthogonal multiple access (NOMA), universal filtered multicarrier (UFMC), and filter bank multiple carriers (FBMC) [6][7][8]. Among these, GFDM is deliberated as an encouraging non-orthogonal candidate waveform technology that effectively resolves the OFDM flaws for networks beyond 5G [9].…”

“…The complexity of receiver design has been increased by all the interferences. In GLCM, cyclic suffix (CS) and cyclic prefix (CP) are dispensed to the whole block rather than a symbol that boosts the spectral efficiency (SE) and eases the associated synchronization requirements in machine-type communications (MTC) [15,16]. The use of MIMO techniques can further enhance the performance of GFDM systems.…”

Intelligent Optimization of PC-GFDM Transceiver

“…The primary motivation of preference for GFDM is the flexible use of a multi-carrier filter bank. The spectrum region is split into a set of non-orthogonally spectral segments by a developed method to reduce the emission [12]. Hence removed the orthogonality restrictions related to subcarrier spacing and applied the filtration at each subcarrier.…”

“…Hence removed the orthogonality restrictions related to subcarrier spacing and applied the filtration at each subcarrier. The G is flexibly used over the subcarrier level of the waveform [13].…”