http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Beamforming in Vehicle to Infrastructure Scenario with Respect to LSTM and NAR Method
Bhadauria Prateek,Kumar Ravi,Sharma Sanjay 대한전기학회 2024 Journal of Electrical Engineering & Technology Vol.19 No.1
The application of deep learning for adaptive beamforming is a necessary and disruptive advancement in wireless communication technology. It has the potential to satisfy the continuous need for data trafc in a highly dense network created by the vehicle to infrastructure (V2I) scenario. Due to excessive usage of data in V2I scenario interference is a pertinent problem. It is essential to adaptively predict and nullify the interference for V2I scenarios. Practical V2I network implementation is limited because of the inevitability of interference due to the random nature of the wireless channel. This paper proposes an adaptive beamforming (ABF) technique for mitigation of interference in V2I networks, especially in a multiuser environment. In this work, LSTM based deep learning and Non-Linear Auto Regressive (NAR) based regressor have been employed to predict the angles between the RSU’s and UE. Simulation results have confrmed that the proposed LSTM model achieves comparable performance in terms of system throughput when compared with the non-linear auto regressive (NAR) method implemented as an artifcial neural network (ANN).