Deep Learning Based Receivers for IEEE 802.11p Standard with High Power Amplifiers Distortions

Abstract

In recent years, vehicular communication has attracted significant research attention for its potential as a fifth generation (5G) application. The IEEE 802.11p standard enables the wireless technology that defines vehicular communication and, due to the time-varying characteristic, one of its critical challenges is to ensure communication reliability. Moreover, this standard is based on orthogonal frequency division multiplexing (OFDM) transmission scheme, which may suffer from nonlinear distortions induced by high power amplifiers (HPA) at the transmitter, degrading the channel estimation and detection performance of the receivers. In this work, the application of deep learning (DL) based channel estimation schemes to the IEEE 802.11p standard in presence of HPA distortions is presented. Simulation results show that the deep neural network (DNN) based estimation schemes outperform conventional data-pilot aided (DPA) and spectral temporal averaging (STA) estimators in terms of bit error rate and normalized mean squared error, evidencing their superiority in providing reliable estimation in mobility scenarios in presence of HPA nonlinear distortions. Furthermore, the hybrid solution, employing a joint DNNbased post-processing and conventional estimation, achieves less computational complexity than the DL-based proposal on top of the initial DPA estimation.

Low Complexity LSTM-NN-Based Receiver for Vehicular Communications in the Presence of High-Power Amplifier Distortions

“…The authors in [7] show that the trained DNN is capable of learning the channel frequency domain characteristics, preventing the error propagation typical of the DPA method. In addition, although only a V2V communication scenario free of the HPA nonlinear distortions has been considered in [7], we have shown in [19] that DNN-based methods implicitly have some robustness against these nonlinearities. This is different from the case of using only conventional channel estimators, without DNNs, for which the performance is considerably degraded by the HPA distortions.…”

“…DL-based processing has been shown to be an efficient tool to compensate HPA nonlinear effects at the receiver, given the nonlinear nature of the DL architectures and thanks to their generalization properties [17], [18]. In this context, we have compared in [19] different conventional vehicular channel estimators and DL-based methods, with the effect of the nonlinear amplification of OFDM signals based on the polynomial distortion model developed by [20], [21]. Results show that DL-based receivers are intrinsically more robust to the HPA-induced nonlinearities, providing reliable channel estimates even in high-mobility scenarios.…”

“…Results show that DL-based receivers are intrinsically more robust to the HPA-induced nonlinearities, providing reliable channel estimates even in high-mobility scenarios. Nevertheless, the effort in [19] only highlights the robustness of hybrid estimators that combine DNNs with conventional methods, inspiring this work toward designing novel receiver architectures.…”

“…In this paper, we propose a novel receiver for vehicular communications subject to HPA-induced distortions, exploiting the features of the channel in the frequency domain. It is worth pointing out that both nonlinear and the relative smoothness in the frequency domain characteristics of the [4] 2013 ✓ Kim et al [5] 2014 ✓ Han et al [7] 2019 ✓ ✓ Gizzini et al [24] 2020 ✓ ✓ ✓ Zhu et al [8] 2020 ✓ ✓ Gizzini et al [9] 2021 ✓ ✓ Pan et al [11] 2021 ✓ ✓ ✓ Gizzini et al [12] 2021 ✓ ✓ ✓ ✓ Mattu et al [22] 2022 ✓ ✓ Gizzini et al [23] 2022 ✓ Dos Reis et al [19] 2022…”