A deep learning-aided temporal spectral ChannelNet for IEEE 802.11p-based channel estimation in vehicular communications

In vehicular communications using IEEE 802.11p, estimating channel frequency response (CFR) is a remarkably challenging task. The challenge for channel estimation (CE) lies in tracking variations of CFR due to the extremely fast time-varying characteristic of channel and low density pilot. To tackle such problem, inspired by image super-resolution (ISR) techniques, a deep learning-based temporal spectral channel network (TS-ChannelNet) is proposed. Following the process of ISR, an average decision-directed estimation with time truncation (ADD-TT) is first presented to extend pilot values into tentative CFR, thus tracking coarsely variations. Then, to make tentative CFR values accurate, a super resolution convolutional long short-term memory (SR-ConvLSTM) is utilized to track channel extreme variations by extracting sufficiently temporal spectral correlation of data symbols. Three representative vehicular environments are investigated to demonstrate the performance of our proposed TS-ChannelNet in terms of normalized mean square error (NMSE) and bit error rate (BER). The proposed method has an evident performance gain over existing methods, reaching about 84.5% improvements at some high signal-noise-ratio (SNR) regions.

[1]  Mihaela van der Schaar,et al.  Machine Learning in the Air , 2019, IEEE Journal on Selected Areas in Communications.

[2]  Eylem Ekici,et al.  Wireless Access in Vehicular Environments , 2009, EURASIP J. Wirel. Commun. Netw..

[3]  Wolfgang Utschick,et al.  Learning the MMSE Channel Estimator , 2017, IEEE Transactions on Signal Processing.

[4]  Said Benkirane,et al.  Performance Evaluation of IEEE 802.11p and IEEE 802.16e for Vehicular Ad Hoc Networks Using Simulation Tools , 2018, 2018 IEEE 5th International Congress on Information Science and Technology (CiSt).

[5]  Kun-Chan Lan,et al.  A Comparison of 802.11a and 802.11p for V-to-I Communication: A Measurement Study , 2010, QSHINE.

[6]  Xiao Ke,et al.  End-to-End Automatic Image Annotation Based on Deep CNN and Multi-Label Data Augmentation , 2019, IEEE Transactions on Multimedia.

[7]  Hamid Sheikhzadeh,et al.  Deep Learning-Based Channel Estimation , 2018, IEEE Communications Letters.

[8]  Dit-Yan Yeung,et al.  Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting , 2015, NIPS.

[9]  Geoffrey Ye Li,et al.  Deep-Learning-Based Wireless Resource Allocation With Application to Vehicular Networks , 2019, Proceedings of the IEEE.

[10]  Abdul Hanan Abdullah,et al.  EETP-MAC: energy efficient traffic prioritization for medium access control in wireless body area networks , 2020, Telecommun. Syst..

[11]  Naixue Xiong,et al.  A Game Theory Algorithm for Intra-Cluster Data Aggregation in a Vehicular Ad Hoc Network , 2016, Sensors.

[12]  Wen-Tsuen Chen,et al.  An IEEE 802.11p Based Distributed Channel Assignment Scheme Considering Emergency Message Dissemination , 2012, 2012 IEEE 75th Vehicular Technology Conference (VTC Spring).

[13]  Javed Iqbal,et al.  Traffic priority based delay-aware and energy efficient path allocation routing protocol for wireless body area network , 2019, J. Ambient Intell. Humaniz. Comput..

[14]  Geoffrey Ye Li,et al.  Power of Deep Learning for Channel Estimation and Signal Detection in OFDM Systems , 2017, IEEE Wireless Communications Letters.

[15]  Xiaoou Tang,et al.  Image Super-Resolution Using Deep Convolutional Networks , 2014, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[16]  Inkyu Lee,et al.  A New Data Pilot-Aided Channel Estimation Scheme for Fast Time-Varying Channels in IEEE 802.11p Systems , 2019, IEEE Transactions on Vehicular Technology.

[17]  Hongju Cheng,et al.  Data prediction model in wireless sensor networks based on bidirectional LSTM , 2019, EURASIP J. Wirel. Commun. Netw..

[18]  Karim G. Seddik,et al.  Low-Complexity Semi-Blind Channel Estimation Algorithms for Vehicular Communications Using the IEEE 802.11p Standard , 2019, IEEE Transactions on Intelligent Transportation Systems.

[19]  Lei Zhang,et al.  Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising , 2016, IEEE Transactions on Image Processing.

[20]  Yang Yang.  Broadcast encryption based non-interactive key distribution in MANETs , 2014, J. Comput. Syst. Sci..

[21]  Nan Cheng,et al.  Deep-Learning-Based Joint Optimization of Renewable Energy Storage and Routing in Vehicular Energy Network , 2020, IEEE Internet of Things Journal.

[22]  Xiang Cheng,et al.  Constructed Data Pilot-Assisted Channel Estimators for Mobile Environments , 2015, IEEE Transactions on Intelligent Transportation Systems.

[23]  Xiaoli Ma,et al.  Deep Learning-Based Channel Estimation for Doubly Selective Fading Channels , 2019, IEEE Access.

[24]  B. V. K. Vijaya Kumar,et al.  Performance of the 802.11p Physical Layer in Vehicle-to-Vehicle Environments , 2012, IEEE Transactions on Vehicular Technology.

[25]  Fasee Ullah,et al.  An improved supervisory protocol for automatic selection of routing protocols in environment-aware vehicular ad hoc networks , 2018, Int. J. Distributed Sens. Networks.

[26]  Mohsen Guizani,et al.  5G Vehicular Network Resource Management for Improving Radio Access Through Machine Learning , 2020, IEEE Access.

[27]  Mary Ann Ingram,et al.  Six Time- and Frequency-Selective Empirical Channel Models for Vehicular Wireless LANs , 2007, 2007 IEEE 66th Vehicular Technology Conference.

[28]  Peng Dai,et al.  A novel steganalysis method with deep learning for different texture complexity images , 2018, Multimedia Tools and Applications.

[29]  Geoffrey Ye Li,et al.  Deep Learning-Based CSI Feedback Approach for Time-Varying Massive MIMO Channels , 2018, IEEE Wireless Communications Letters.