Temporal Averaging LSTM-based Channel Estimation Scheme for IEEE 802.11p Standard

Gizzini, Abdul Karim; Chafii, Marwa; Ehsanfar, Shahab; Shubair, Raed M.

doi:10.1109/globecom46510.2021.9685409

“…The authors in [43] propose to use only LSTM network instead of two as implemented in the LSTM-FNN-DPA estimator. In addition, noise compensation is made possible by applying time averaging (TA) processing as shown in Figure 6.…”

Section: E Lstm-dpa-tamentioning

confidence: 99%

“…The ADD-TT interpolation first applies the DPA estimation requiring 18K on multiplications/divisions and 8K on summations/subtractions. The time-domain truncation operation applied in (43) requires 4LK on multiplications as well as 5K on L − 2K on summations. In the ADD-TT interpolation, the frequency-domain averaging (44) requires 10K on summations and 2K on multiplications.…”

Section: ) Ts-channelnet Estimatormentioning

confidence: 99%

A Survey on Deep Learning Based Channel Estimation in Doubly Dispersive Environments

Gizzini

¹

,

Chafii

²

2022

Self Cite

View full text Add to dashboard Cite

Wireless communications systems are impacted by multi-path fading and Doppler shift in dynamic environments, where the channel becomes doubly-dispersive and its estimation becomes an arduous task. Only a few pilots are used for channel estimation in conventional approaches to preserve high data rate transmission. Consequently, such estimators experience a significant performance degradation in high mobility scenarios. Recently, deep learning has been employed for doubly-dispersive channel estimation due to its low-complexity, robustness, and good generalization ability. Against this backdrop, the current paper presents a comprehensive survey on channel estimation techniques based on deep learning by deeply investigating different methods. The study also provides extensive experimental simulations followed by a computational complexity analysis. After considering different parameters such as modulation order, mobility, frame length, and deep learning architecture, the performance of the studied estimators is evaluated in several mobility scenarios. In addition, the source codes are made available online in order to make the results reproducible.

show abstract

“…Finally, to alleviate the impact of the AWGN noise, TA processing is applied to the ĥLSTM-DPA Here, α denotes the utilized weighting coefficient. In [43], the authors use a fixed α = 2 for simplicity. Therefore, the TA applied in (35) reduces the AWGN noise power σ 2 iteratively within the received OFDM frame according to the ratio R DL-TA q = 1 4…”

Section: E Lstm-dpa-tamentioning

confidence: 99%

A Survey on Deep Learning based Channel Estimation in Doubly Dispersive Environments

Gizzini¹,

Chafii²

2022

Preprint

Self Cite

View full text Add to dashboard Cite

Wireless communications systems are impacted by multi-path fading and Doppler shift in dynamic environments, where the channel becomes doubly-dispersive and its estimation becomes an arduous task. Only a few pilots are used for channel estimation in conventional approaches to preserve high data rate transmission. Consequently, such estimators experience a significant performance degradation in high mobility scenarios. Recently, deep learning has been employed for doubly-dispersive channel estimation due to its low-complexity, robustness, and good generalization ability. Against this backdrop, the current paper presents a comprehensive survey on channel estimation techniques based on deep learning by deeply investigating different methods. The study also provides extensive experimental simulations followed by a computational complexity analysis. After considering different parameters such as modulation order, mobility, frame length, and deep learning architecture, the performance of the studied estimators is evaluated in several mobility scenarios. In addition, the source codes are made available online in order to make the results reproducible.

show abstract

“…In addition, further classical and Bayesian approaches of the DPA scheme has been studied in [2] and references therein. Recently, different machine learning approaches based on deep neural networks (DNN) have been studied in order to improve the channel estimation performance for 802.11p [3], [4], [5], [6]. In general however, if the wireless channel is harshly doubly-dispersive, the DPA based derivations of the channel estimation become less effective, because the adjacent subcarriers and symbols tend to lose their spectral and temporal correlations, and also erroneous demapping of initial symbols causes the error to propagate through the entire transmit frame.…”

Section: Introductionmentioning

confidence: 99%

Performance Comparison of IEEE 802.11p, 802.11bd-draft and a Unique-Word-based PHY in Doubly-Dispersive Channels

Ehsanfar

¹

,

Moessner

²

,

Gizzini

³

et al. 2022

2022 IEEE Wireless Communications and Networking Conference (WCNC)

Self Cite

View full text Add to dashboard Cite

In this paper, we evaluate and make a comparison of the channel estimation performance for three different frame structures of IEEE 802.11p, IEEE 802.11bd-draft and a unique-word (UW)-based physical layer (PHY). As in vehicle-toeverything communication the wireless channel conditions may vary significantly depending on the environment and vehicle velocity, severe fading in both time and frequency domains may occur. Through simulation results, we show that the UWbased PHY achieves an interference-free performance of channel estimation via a low complexity technique, whereas the 802.11bd would need to employ a high complexity approach in order to achieve a comparable estimation performance.

show abstract

Temporal Averaging LSTM-based Channel Estimation Scheme for IEEE 802.11p Standard

Cited by 35 publications

References 9 publications

A Survey on Deep Learning Based Channel Estimation in Doubly Dispersive Environments

A Survey on Deep Learning Based Channel Estimation in Doubly Dispersive Environments

A Survey on Deep Learning based Channel Estimation in Doubly Dispersive Environments

Performance Comparison of IEEE 802.11p, 802.11bd-draft and a Unique-Word-based PHY in Doubly-Dispersive Channels

Contact Info

Product

Resources

About