Recurrent Neural Networks with Long Short-Term Memory for Fading Channel Prediction

With the aid of accurate channel state information (CSI) at the transmitter, a wireless system can receive great performance by adaptively selecting its transmission parameters. However, the CSI becomes outdated quickly due to the rapid channel variation caused by multi-path fading, leading to severe performance degradation. Such an impact is applicable on a wide variety of adaptive transmission systems, the fading channel prediction that can combat the outdated CSI is therefore of great significance. The aim of this paper is to propose two novel recurrent neural network (RNN)-based predictors, leveraging the strong time-series prediction capability of long short-term memory or gated recurrent unit. Performance evaluation is conducted and the results in terms of prediction accuracy verify that the proposed predictors notably outperform the conventional RNN predictor.

[1]  Gonzalo Seco-Granados,et al.  Opportunistic relay selection with outdated CSI: outage probability and diversity analysis , 2009, IEEE Transactions on Wireless Communications.

[2]  Mohamed-Slim Alouini,et al.  An Overview of Physical Layer Security in Wireless Communication Systems With CSIT Uncertainty , 2016, IEEE Access.

[3]  Jiang Wang,et al.  Unified Performance Analysis of Transmit Antenna Selection With OSTBC and Imperfect CSI Over Nakagami- m Fading Channels , 2018, IEEE Transactions on Vehicular Technology.

[4]  Bhaskar D. Rao,et al.  Capacity Analysis of MIMO Systems Using Limited Feedback Transmit Precoding Schemes , 2008, IEEE Transactions on Signal Processing.

[5]  Jing Zhang,et al.  Resource Allocation in OFDMA Networks With Imperfect Channel State Information , 2014, IEEE Communications Letters.

[6]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[7]  Robert W. Heath,et al.  An overview of limited feedback in wireless communication systems , 2008, IEEE Journal on Selected Areas in Communications.

[8]  Wei Jiang,et al.  Neural Network-Based Channel Prediction and Its Performance in Multi-Antenna Systems , 2018, 2018 IEEE 88th Vehicular Technology Conference (VTC-Fall).

[9]  Demis Hassabis,et al.  Mastering the game of Go with deep neural networks and tree search , 2016, Nature.

[10]  Alexandra Duel-Hallen,et al.  Fading Channel Prediction for Mobile Radio Adaptive Transmission Systems , 2007, Proceedings of the IEEE.

[11]  Les E. Atlas,et al.  Recurrent neural networks and robust time series prediction , 1994, IEEE Trans. Neural Networks.

[12]  Lie-Liang Yang,et al.  Recurrent Neural Network Based Narrowband Channel Prediction , 2006, 2006 IEEE 63rd Vehicular Technology Conference.

[13]  Yoshua Bengio,et al.  Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation , 2014, EMNLP.

[14]  Wei Jiang,et al.  A Comparison of Wireless Channel Predictors: Artificial Intelligence Versus Kalman Filter , 2019, ICC 2019 - 2019 IEEE International Conference on Communications (ICC).

[15]  Hans D. Schotten,et al.  Recurrent Neural Network-Based Frequency-Domain Channel Prediction for Wideband Communications , 2019, 2019 IEEE 89th Vehicular Technology Conference (VTC2019-Spring).

[16]  Wei Jiang,et al.  Neural Network–Based Wireless Channel Prediction , 2020 .

[17]  Larry J. Greenstein,et al.  Multi-User and Single-User Throughputs for Downlink MIMO Channels with Outdated Channel State Information , 2014, IEEE Wireless Communications Letters.

[18]  Akira Hirose,et al.  Fading Channel Prediction Based on Combination of Complex-Valued Neural Networks and Chirp Z-Transform , 2014, IEEE Transactions on Neural Networks and Learning Systems.

[19]  Wei Jiang,et al.  Multi-Antenna Fading Channel Prediction Empowered by Artificial Intelligence , 2018, 2018 IEEE 88th Vehicular Technology Conference (VTC-Fall).

[20]  Kien T. Truong,et al.  Effects of channel aging in massive MIMO systems , 2013, Journal of Communications and Networks.

[21]  Mei Song,et al.  Effect of Outdated CSI on Handover Decisions in Dense Networks , 2017, IEEE Communications Letters.

[22]  Wei Jiang,et al.  A Robust Opportunistic Relaying Strategy for Co-Operative Wireless Communications , 2016, IEEE Transactions on Wireless Communications.

[23]  Paul D. Teal,et al.  Extrapolation of MIMO Mobile-to-Mobile Wireless Channels Using Parametric-Model-Based Prediction , 2015, IEEE Transactions on Vehicular Technology.

[24]  Hans D. Hallen,et al.  Long-range prediction of fading signals , 2000, IEEE Signal Process. Mag..

[25]  Hong Wen,et al.  The Rayleigh Fading Channel Prediction via Deep Learning , 2018, Wirel. Commun. Mob. Comput..

[26]  Jwo-Yuh Wu,et al.  Optimal Linear Channel Prediction for LTE-A Uplink Under Channel Estimation Errors , 2013, IEEE Transactions on Vehicular Technology.

[27]  Tharmalingam Ratnarajah,et al.  Performance Analysis of IA Techniques in the MIMO IBC With Imperfect CSI , 2015, IEEE Transactions on Communications.

[28]  Wei Jiang,et al.  Neural Network-Based Fading Channel Prediction: A Comprehensive Overview , 2019, IEEE Access.