Channel Estimation Based on Deep Learning in Vehicle-to-Everything Environments

Pan, Jie; Shan, Hangguan; Li, Rongpeng; Wu, Yongping; Wu, Weihua; Quek, Tony Q. S.

doi:10.1109/lcomm.2021.3059922

Cited by 54 publications

(53 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…. do compute the sliding-time window width θ = min{⌈µt α ⌉, t} compute qj,t,T t,θ (14) and then qSW-UCB# j,t,T t,θ (15) select power level j for transmission at time-slot t using (9) receive packet from S and transmit it to D nj,t+1 ← nj,t + 1 {I t =j} for all j if reception and transmission are successful then rj,t = 1 end end non-stationary is negligible (if any), as shown in Fig. 10 in Section V, for the period of time that the channel is strict-sense stationary.…”

Section: ) Non-stationary Channelsmentioning

confidence: 99%

“…In industrial settings, Lu et al [13] calculate the non-stationary Rician channel parameters through a non-data aided method, based on the Gaussian mixture model and iterative sub-component discrimination, achieving nearoptimal estimation accuracy. In vehicle-to-everything (V2X) networks, Pan et al [14] propose data pilot-aided (DPA) deep learning-based channel estimation, exploiting de-mapped data symbols as pilots. DPA is integrated with a long shortterm memory network and a multi-layer perceptron network to obtain time-frequency correlation.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Bandit-Based Power Control in Full-Duplex Cooperative Relay Networks With Strict-Sense Stationary and Non-Stationary Wireless Communication Channels

Νομικός

Talebi

Charalambous

et al. 2022

IEEE Open J. Commun. Soc.

View full text Add to dashboard Cite

Full-duplex relaying is an enabling technique of sixth generation (6G) mobile networks, promising tremendous rate and spectral efficiency gains. In order to improve the performance of full-duplex communications, power control is a viable way of avoiding excessive loop interference at the relay. Unfortunately, power control requires channel state information of source-relay, relaydestination and loop interference channels, thus resulting in increased overheads. Aiming to offer a low-complexity alternative for power control in such networks, we adopt reward-based learning in the sense of multi-armed bandits. More specifically, we present bandit-based power control, relying on acknowledgements/negative-acknowledgements observations by the relay. Our distributed algorithms avoid channel state information acquisition and exchange, and can alleviate the impact of outdated channel state information. Two cases are examined regarding the channel statistics of the wireless network, namely, strict-sense stationary and non-stationary channels. For the latter, a sliding window approach is adopted to further improve the performance. Performance evaluation highlights a performance-complexity trade-off, compared to optimal power control with full channel knowledge and significant gains over cases considering channel estimation and feedback overheads, outdated channel knowledge, no power control and random power level selection. Finally, it is shown that the sliding-window bandit-based algorithm provides improved performance in non-stationary settings by efficiently adapting to abrupt changes of the wireless channels.

show abstract

Section: ) Non-stationary Channelsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Bandit-Based Power Control in Full-Duplex Cooperative Relay Networks With Strict-Sense Stationary and Non-Stationary Wireless Communication Channels

Νομικός

Talebi

Charalambous

et al. 2022

IEEE Open J. Commun. Soc.

View full text Add to dashboard Cite

show abstract

“…A review of ML-based resource allocation approaches in DSRC networks can be found in [287]. Examples of using ML for improving 802.11p performance include: using DRL for per-link band and transmission power allocation [292], RL for tuning the CW size [293]- [295], Q-learning for improving handoff decisions [296], improving transmission control protocol (TCP) performance with federated learning [297], DNNs for channel estimation [298], and using RL for selecting the data transmission rate in a high-mobility scenario [286], [299].…”

Section: Vehicular Networkmentioning

confidence: 99%

Wi-Fi Meets ML: A Survey on Improving IEEE 802.11 Performance with Machine Learning

Szott,

Kosek-Szott,

Gawłowicz

et al. 2021

Preprint

View full text Add to dashboard Cite

Wireless local area networks (WLANs) empowered by IEEE 802.11 (WiFi) hold a dominant position in providing Internet access thanks to their freedom of deployment and configuration as well as affordable and highly interoperable devices. The WiFi community is currently deploying WiFi 6 and developing WiFi 7, which will bring higher data rates, better multi-user and multi-AP support, and, most importantly, improved configuration flexibility. These technical innovations, including the plethora of configuration parameters, are making next-generation WLANs exceedingly complex as the dependencies between parameters and their joint optimization usually have a non-linear impact on network performance. The complexity is further increased in the case of dense deployments and coexistence in shared bands. While classic optimization approaches fail in such conditions, machine learning (ML) is well known for being able to handle complexity. Much research has been published on using ML to improve WiFi performance and solutions are slowly being adopted in existing deployments. In this survey, we adopt a structured approach to describing the various areas where WiFi can be enhanced using ML. To this end, we analyze over 200 papers in the field providing readers with an overview of the main trends. Based on this review, we identify both open challenges in each WiFi performance area as well as general future research directions.

show abstract

“…Jing et al. [19] proposed a novel long short‐term memory and multilayer perceptron based channel estimation scheme with a data pilot‐aided method, which could be effectively used in the fast time‐varying vehicle channel environments. A bidirectional gated recurrent unit based method was proposed to improve the channel estimation in [20], and it showed better performance than traditional methods.…”

Section: Introductionmentioning

confidence: 99%

“…Huaiyin et al [18] devised a DL based joint channel classification, channel estimation and signal detection scheme to identify the water types and improve link performances in various underwater wireless optical communication environments. Jing et al [19] proposed a novel long short-term memory and multilayer perceptron based channel estimation scheme with a data pilot-aided method, which could be effectively used in the fast time-varying vehicle channel environments. A bidirectional gated recurrent unit based method was proposed to improve the channel estimation in [20], and it showed better performance than traditional methods.…”

Section: Introductionmentioning

confidence: 99%

A model‐driven robust deep learning wireless transceiver

Duan

Xiang

2021

IET Communications

View full text Add to dashboard Cite

Recently, deep learning (DL) has been successfully applied in computer vision and natural language processing. The communication physical layer based on deep learning has received widespread attention. Introducing domain-knowledge into neural networks (NNs), autoencoder based end-to-end communication system, incorporating radio transformer networks (RTNs) (RTNs-AE) has achieved desirable performance with a channel model in the middle layer. The advent of RTNs underscores the power of expertise at DL. However, a tap-length in the design of RTNs network must be assumed, which requires some channel information. To address this issue, a new deep learning wireless transceiver named pilot-aided autoencoder (PA-AE) is proposed. It can decode on a multipath fading channel without knowing the channel information and the equalization module design. The proposed scheme introduces a well-designed auxiliary pilot, which carries the learned channel information into decoding with the transmitted signal. The decoding part recovers the sent information from the collected signal without specially designed modules for parameter estimation and equalization.This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.

show abstract

Channel Estimation Based on Deep Learning in Vehicle-to-Everything Environments

Cited by 54 publications

References 14 publications

Bandit-Based Power Control in Full-Duplex Cooperative Relay Networks With Strict-Sense Stationary and Non-Stationary Wireless Communication Channels

Bandit-Based Power Control in Full-Duplex Cooperative Relay Networks With Strict-Sense Stationary and Non-Stationary Wireless Communication Channels

Wi-Fi Meets ML: A Survey on Improving IEEE 802.11 Performance with Machine Learning

A model‐driven robust deep learning wireless transceiver

Contact Info

Product

Resources

About