CSI Feedback Method Based on Deep Learning for FDD Massive MIMO Systems
LIAO Yong1, YAO Hai-mei1, HUA Yuan-xiao1, ZHAO Yan2
1. Center of Communication and TT&C, Chongqing University, Chongqing 400044, China;
2. 61212 Unit of the People's Liberation Army, Beijing 100043, China
Abstract：Existing channel state information (CSI) feedback methods for frequency division duplexing (FDD) multiple-input multiple-output (MIMO) systems have high complexity and low feedback accuracy.In this paper,a deep learning-based CSI compression feedback method is proposed.The method first uses the convolutional neural network (CNN) to extract the channel feature vector,and then uses the maximum pooling (Maxpooling) network to compress the CSI.Finally,considering the spatial correlation of the massive MIMO channel,bidirectional long short-term memory (Bi-LSTM) network and bidirectional convolution long-term memory (Bi-ConvLSTM) network are used for single-user and multi-user scenarios respectively to recover the CSI.In this paper,the deep learning network is trained offline using massive MIMO channel data,the channel information learned by the network can fully characterize the states of the channel.The simulation results show that compared with the existing typical CSI feedback methods,the proposed method has higher feedback accuracy,shorter running time and better system performance.
[1] Larsson E G,Edfors O,Tufvesson F,et al.Massive MIMO for next generation wireless systems[J].IEEE Communications Magazine,2014,52(2):186-195.
[2] Barriac G,Madhow U.Space-time communication for OFDM with implicit channel feedback[J].IEEE Transactions on Information Theory,2004,50(12):3111-3129.
[3] Tseng C C,Wu J Y,Lee T S.Enhanced compressive downlink CSI recovery for FDD massive MIMO systems using weighted block 1-minimization[J].IEEE Transactions on Communications,2016,64(3):1055-1067.
[4] Kuo P H,Kung H T,Ting P A.Compressive sensing based channel feedback protocols for spatially-correlated massive antenna arrays[A].Wireless Communications and Networking Conference[C].Shanghai,China:IEEE,2012.492-497.
[5] Min S S,Chae C B.Compressed channel feedback for correlated massive MIMO systems[A].Globecom Workshops[C].Austin,TX,USA:IEEE,2014.327-332.
[6] Ge A,Zhang T,Hu Z,et al.Principal component analysis based limited feedback scheme for massive MIMO systems[A].Personal,Indoor,and Mobile Radio Communications[C].Hong Kong:IEEE,2015.326-331.
[7] Wang T Q,Wen C K,Wang H Q,et al.Deep learning for wireless physical layer:opportunities and challenges[J].China Communications,2017,14(11):92-111.
[8] Liao Y,Hua Y X,Yao H M,Yang X Y.ChanEstNet:a deep learning based channel estimation for high-speed scenarios[A].International Conference on Communications[C].Shanghai,China:IEEE,2019.1-6.
[9] Ye H,Li G Y,Juang B H.Power of deep learning for channel estimation and signal detection in OFDM systems[J].IEEE Wireless Communications Letters,2018,7(1):114-117.
[10] Xu W,Zhong Z,Be'Ery Y,et al.Joint neural network equalizer and decoder[A].International Symposium on Wireless Communication Systems[C].Lisbon,Portugal:IEEE,2018.1-5.
[11] Wen C K,Shih W T,Jin S.Deep learning for massive MIMO CSI feedback[J].IEEE Wireless Communications Letters,2017,7(5):748-751.
[12] Iqbal R,Abhayapala T D,Lamahewa T A.Generalised clarke model for mobile-radio reception[J].IET Communications,2009,3(4):644-654.
2020, Vol. 48 
