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

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

扫码查看
原文链接
  • NETL
  • NSTL
  • Wiley
In order to enhance communication while minimizing complexity in 5Gand beyond,MIMO-OFDMsystems need accurate channel prediction. In order to enhance channel prediction, decrease ErrorVector Magnitude, Peak Power, and Adjacent Channel Leakage Ratio, this study employs thePyramidal Dilation Attention Convolutional Neural Network (PDACNN). Simplified clipping withfiltering (SCF) reduces PAPR data, and this technique employs a PDACNN trained with thereduced data. By combining attention techniques with pyramidal dilated convolutions, the suggestedPDACNN architecture is able to extract OFDM channel parameters across several scales. Attentionapproaches enhance channel prediction by allowing the model to dynamically concentrate onessential information. The primary objective is to make use of the network’s ability to comprehendintricate spatial–temporal connections in OFDM channel data. The goal of these techniques is tomake channel forecasts more accurate and resilient while decreasing concerns about EVM, PeakPower, 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-noiseratio (SNR), and throughput. Throughput gains of 23.76%, 30.45%, and 18.97% are achieved viaCP-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.

bit error ratechannel predictionMIMO-OFDMPAPRpyramidal dilation attention convolutional neural network

Chirakkal Radhakrishnan Rathish、Balakrishnan Manojkumar、Lakshmanaperumal Thanga Mariappan、Panchapakesan Ashok、Udayakumar Arun Kumar、Krishnan Balan

展开 >

Department of Computer Engineering, NewHorizon College of Engineering, Bengaluru,India

Department of Electronics andCommunication Engineering, KarpagamInstitute of Technology, Coimbatore, India

Department of Smart Computing, School ofComputer Science Engineering and InformationSystems, Vellore Institute of Technology,Vellore, India

Symbiosis Institute of Digital and TelecomManagement (SIDTM), Symbiosis International(Deemed University) (SIU), Pune, India

Department of Electrical and ElectronicsEngineering, Faculty of Engineering, KarpagamAcademy of Higher Education (Deemed to beUniversity), Coimbatore, India

Department of Electrical and ElectronicsEngineering, Government College ofTechnology, Coimbatore, India

展开 >

2025

10.1002/itl2.532

Internet Technology Letters

Internet Technology Letters

ISSN：
年,卷(期)：2025.8(2)
  • 22