Deep Learning for Massive MIMO Channel State Acquisition and Feedback
Tóm tắt
Massive multiple-input multiple-output (MIMO) systems are a main enabler of the excessive throughput requirements in 5G and future generation wireless networks as they can serve many users simultaneously with high spectral and energy efficiency. To achieve this massive MIMO systems require accurate and timely channel state information (CSI), which is acquired by a training process that involves pilot transmission, CSI estimation, and feedback. This training process incurs a training overhead, which scales with the number of antennas, users, and subcarriers. Reducing the training overhead in massive MIMO systems has been a major topic of research since the emergence of the concept. Recently, deep learning (DL)-based approaches have been proposed and shown to provide significant reduction in the CSI acquisition and feedback overhead in massive MIMO systems compared to traditional techniques. In this paper, we present an overview of the state-of-the-art DL architectures and algorithms used for CSI acquisition and feedback, and provide further research directions.
Tài liệu tham khảo
Marzetta TL (2010) Noncooperative cellular wireless with unlimited numbers of base station antennas. IEEE Trans Wirel Commun 9(11):3590–3600. https://doi.org/10.1109/TWC.2010.092810.091092
Rusek F, Persson D, Lau BK, Larsson EG, Marzetta TL, Edfors O, Tufvesson F (2013) Scaling up MIMO: opportunities and challenges with very large arrays. IEEE Signal Process Mag 30(1):40–60. https://doi.org/10.1109/MSP.2011.2178495
Marzetta TL (2006) How much training is required for multiuser MIMO? In: 2006 fortieth asilomar conference on signals, systems and computers, pp 359–363. https://doi.org/10.1109/ACSSC.2006.354768
Adhikary A, Nam J, Ahn J, Caire G (2013) Joint spatial division and multiplexing—the large-scale array regime. IEEE Trans Inf Theory 59(10):6441–6463. https://doi.org/10.1109/TIT.2013.2269476
Jiang Z, Molisch AF, Caire G, Niu Z (2015) Achievable rates of FDD massive MIMO systems with spatial channel correlation. IEEE Trans Wirel Commun 14(5):2868–2882. https://doi.org/10.1109/TWC.2015.2396058
Flordelis J, Rusek F, Tufvesson F, Larsson EG, Edfors O (2018) Massive MIMO performance—TDD versus FDD: what do measurements say? IEEE Trans Wirel Commun 17(4):2247–2261. https://doi.org/10.1109/TWC.2018.2790912
Björnson E, Larsson EG, Marzetta TL (2016) Massive MIMO: ten myths and one critical question. IEEE Commun Mag 54(2):114–123. https://doi.org/10.1109/MCOM.2016.7402270
Lu L, Li GY, Swindlehurst AL, Ashikhmin A, Zhang R (2014) An overview of massive MIMO: benefits and challenges. IEEE J Sel Topics Signal Process 8(5):742–758. https://doi.org/10.1109/JSTSP.2014.2317671
Ahmadi S (2013) LTE-advanced: a practical systems approach to understanding 3GPP LTE releases 10 and 11 radio access technologies. Academic Press, London
Eliasi PA, Rangan S, Rappaport TS (2017) Low-rank spatial channel estimation for millimeter wave cellular systems. IEEE Trans Wirel Commun 16(5):2748–2759. https://doi.org/10.1109/TWC.2017.2662687
Li X, Fang J, Li H, Wang P (2018) Millimeter wave channel estimation via exploiting joint sparse and low-rank structures. IEEE Trans Wirel Commun 17(2):1123–1133. https://doi.org/10.1109/TWC.2017.2776108
Gunduz D, de Kerret P, Sidiropoulos ND, Gesbert D, Murthy CR, van der Schaar M (2019) Machine learning in the air. IEEE J Sel Areas Commun 37(10):2184–2199. https://doi.org/10.1109/JSAC.2019.2933969
O’Shea T, Hoydis J (2017) An introduction to deep learning for the physical layer. IEEE Trans Cognit Commun Netw 3(4):563–575. https://doi.org/10.1109/TCCN.2017.2758370
Dörner S, Cammerer S, Hoydis J, t Brink S (2018) Deep learning based communication over the air. IEEE J Sel Topics Signal Process 12(1):132–143. https://doi.org/10.1109/JSTSP.2017.2784180
Bourtsoulatze E, Burth Kurka D, Gunduz D (2019) Deep joint source-channel coding for wireless image transmission. IEEE Trans Cognit Commun Netw 5(3):567–579
3gpp (2003) 3rd generation partnership project (3gpp), tr 25.996, v6.1.0 (2003–09). In: Technical report. http://www.3gpp.org
Kyösti P (2007) WINNER II channel models, DR1.1.2. https://www.ist-winnerorg/WINNER2- Deliverables/D112v11pdf
Liu L, Oestges C, Poutanen J, Haneda K, Vainikainen P, Quitin F, Tufvesson F, Doncker PD (2012) The COST 2100 MIMO channel model. IEEE Wireless Commun 19(6):92–99. https://doi.org/10.1109/MWC.2012.6393523
3GPP (2018) Study on channel model for frequencies from 0.5 to 100 GHz. 3rd Generation Partnership Project (3GPP), TR 38901 V1500
Alkhateeb A (2019) DeepMIMO: a generic deep learning dataset for millimeter wave and massive MIMO applications. In: Proceedings of the information theory and applications workshop (ITA), San Diego, pp 1–8
Alkhateeb A, El Ayach O, Leus G, Heath RW (2014) Channel estimation and hybrid precoding for millimeter wave cellular systems. IEEE J Sel Topics Signal Process 8(5):831–846. https://doi.org/10.1109/JSTSP.2014.2334278
Schniter P, Sayeed A (2014) Channel estimation and precoder design for millimeter-wave communications: the sparse way. In: 2014 48th Asilomar conference on signals, systems and computers, pp 273–277. https://doi.org/10.1109/ACSSC.2014
Lee J, Gil G, Lee YH (2014) Exploiting spatial sparsity for estimating channels of hybrid MIMO systems in millimeter wave communications. In: 2014 IEEE global communications conference, pp 3326–3331. https://doi.org/10.1109/GLOCOM.2014.7037320
Alkhateeb A, Leus G, Heath RW (2015) Compressed sensing based multi-user millimeter wave systems: how many measurements are needed? In: 2015 IEEE international conference on acoustics, speech and signal processing (ICASSP), pp 2909–2913. https://doi.org/10.1109/ICASSP.2015.7178503
Dong P, Zhang H, Li GY, Gaspar IS, NaderiAlizadeh N (2019) Deep CNN-based channel estimation for mmwave massive MIMO systems. IEEE J Sel Topics Signal Process 13(5):989–1000. https://doi.org/10.1109/JSTSP.2019.2925975
Shlezinger N, Eldar YC (2019) Deep task-based quantization. arxiv:190806845 eessSP
Kaushik A, Vlachos E, Thompson J, Perelli A (2018) Efficient channel estimation in millimeter wave hybrid MIMO systems with low resolution ADCs. In: 2018 26th European signal processing conference (EUSIPCO), pp 1825–1829. https://doi.org/10.23919/EUSIPCO.2018.8553303
Ding Y, Chiu S, Rao BD (2018) Bayesian channel estimation algorithms for massive MIMO systems with hybrid analog-digital processing and low-resolution ADCs. IEEE J Sel Topics Signal Process 12(3):499–513. https://doi.org/10.1109/JSTSP.2018.2814008
Mo J, Schniter P, Heath RW (2018) Channel estimation in broadband millimeter wave MIMO systems with few-bit ADCs. IEEE Trans Signal Process 66(5):1141–1154
Myers NJ, Tran KN, Jr RWH (2019) Low-rank mmwave MIMO channel estimation in one-bit receivers. arXiv: 191009141 eessSP
Zhang Y, Alrabeiah M, Alkhateeb A (2019) Deep learning for massive MIMO with 1-bit ADCs: when more antennas need fewer pilots. arXiv: 191006960 csIT
Balevi E, Andrews JG (2019) Two-stage learning for uplink channel estimation in one-bit massive MIMO. arxiv: 191112461 eessSP
Gao S, Dong P, Pan Z, Li GY (2019) Deep learning based channel estimation for massive MIMO with mixed-resolution ADCs. IEEE Commun Lett 23(11):1989–1993. https://doi.org/10.1109/LCOMM.2019.2936393
Wen CK, Shih WT, Jin S (2018) Deep learning for massive MIMO CSI feedback. IEEE Wirel Commun Lett 7(5):748–751
Wang T, Wen C, Jin S, Li GY (2019) Deep learning-based CSI feedback approach for time-varying massive MIMO channels. IEEE Wirel Commun Lett 8(2):416–419. https://doi.org/10.1109/LWC.2018.2874264
Lu C, Xu W, Shen H, Zhu J, Wang K (2019) MIMO channel information feedback using deep recurrent network. IEEE Wirel Commun Lett 23(1):188–191. https://doi.org/10.1109/LCOMM.2018.2882829
Liu Z, Zhang L, Ding Z (2019) Exploiting bi-directional channel reciprocity in deep learning for low rate massive MIMO CSI feedback. IEEE Wirel Commun Lett. https://doi.org/10.1109/LWC.2019.2898662
Jang Y, Kong G, Jung M, Choi S, Kim I (2019) Deep autoencoder based CSI feedback with feedback errors and feedback delay in FDD massive MIMO systems. IEEE Wirel Commun Lett 8(3):833–836. https://doi.org/10.1109/LWC.2019.2895039
Guo J, Wen C, Jin S, Li GY (2020) Convolutional neural network based multiple-rate compressive sensing for massive MIMO CSI feedback: Design, simulation, and analysis. IEEE Trans Wirel Commun 1–1. https://doi.org/10.1109/TWC.2020.2968430
Yang Q, Mashhadi MB, Gunduz D (2019) Deep convolutional compression for massive MIMO CSI feedback. In: 2019 IEEE 29th international workshop on machine learning for signal processing (MLSP), pp 1–6. https://doi.org/10.1109/MLSP.2019.8918798
Yang Q, Mashhadi MB, Gunduz D (2020) Distributed deep convolutional compression for massive MIMO CSI feedback. arXiv: 200304684 eessSP
Marpe D, Schwarz H, Wiegand T (2003) Context-based adaptive binary arithmetic coding in the h. 264/avc video compression standard. IEEE Trans Circuits Syst Video Tech 13(7):620–636
Lu Z, Wang J, Song J (2019) Multi-resolution CSI feedback with deep learning in massive MIMO system. arXiv: 191014322 csIT
Mashhadi MB, Yang Q, Gunduz D (2020) CNN-based analog CSI feedback in FDD MIMO-OFDM systems. In: 2020 IEEE 45th international conference on acoustics, speech, and signal processing (ICASSP)
Polyanskiy Y, Poor HV, Verdú S (2010) Channel coding rate in the finite blocklength regime. IEEE Trans Inf Theory 56(5):2307–2359
Wyner A, Ziv J (1976) The rate-distortion function for source coding with side information at the decoder. IEEE Trans Inf Theory 22(1):1–10. https://doi.org/10.1109/TIT.1976.1055508
Guo J, Yang X, Wen CK, Jin S, Li GY (2020) DL-based CSI feedback and cooperative recovery in massive MIMO. arXiv: 200303303 csIT
Alrabeiah M, Alkhateeb A (2019) Deep learning for TDD and FDD massive MIMO: mapping channels in space and frequency. arxiv:190503761 csIT
Yang Y, Gao F, Li GY, Jian M (2019) Deep learning-based downlink channel prediction for FDD massive MIMO system. IEEE Commun Lett 23(11):1994–1998. https://doi.org/10.1109/LCOMM.2019.2934851