Enhanced channel prediction in large-scale 5G MIMO-OFDM systems using pyramidal dilation attention convolutional neural network

Abstract

In order to enhance communication while minimizing complexity in 5G and beyond, MIMO-OFDM systems need accurate channel prediction. In order to enhance channel prediction, decrease Error Vector Magnitude, Peak Power, and Adjacent Channel Leakage Ratio, this study employs the Pyramidal Dilation Attention Convolutional Neural Network (PDACNN). Simplified clipping with filtering (SCF) reduces PAPR data, and this technique employs a PDACNN trained with the reduced data. By combining attention techniques with pyramidal dilated convolutions, the suggested PDACNN architecture is able to extract OFDM channel parameters across several scales. Attention approaches enhance channel prediction by allowing the model to dynamically concentrate on essential information. The primary objective is to make use of the network's ability to comprehend intricate spatial–temporal connections in OFDM channel data. The goal of these techniques is to make channel forecasts more accurate and resilient while decreasing concerns about EVM, Peak Power, and ACLR. To confirm the effectiveness of the suggested CP-LSMIMO-OFDM-PDACNN, we measure its spectral efficiency, peak-to-average power ratio, bit error rate (BER), signal-to-noise ratio (SNR), and throughput. Throughput gains of 23.76%, 30.45%, and 18.97% are achieved via CP-LSMIMO-OFDM-PDACNN, while bit error rates of 20.67%, 12.78%, and 19.56% are reduced. PAPRs of 21.66%, 23.09%, and 25.11% are also decreased.