Full Text:   <522>

Summary:  <16>

CLC number: TN92

On-line Access: 2020-10-14

Received: 2019-09-27

Revision Accepted: 2020-03-27

Crosschecked: 2020-05-18

Cited: 0

Clicked: 259

Citations:  Bibtex RefMan EndNote GB/T7714

 ORCID:

Jun Wang

https://orcid.org/0000-0002-8127-9124

Rong Li

https://orcid.org/0000-0003-1040-1484

-   Go to

Article info.
Open peer comments

Frontiers of Information Technology & Electronic Engineering  2020 Vol.21 No.10 P.1413-1425

http://doi.org/10.1631/FITEE.1900527


Artificial intelligence and wireless communications


Author(s):  Jun Wang, Rong Li, Jian Wang, Yi-qun Ge, Qi-fan Zhang, Wu-xian Shi

Affiliation(s):  Wireless Technology Laboratory, Huawei Technologies Co., Ltd., Hangzhou 310051, China; more

Corresponding email(s):   justin.wangjun@huawei.com, lirongone.li@huawei.com, wangjian23@huawei.com, yiqun.ge@huawei.com, qifan.zhang@huawei.com, wuxian.shi@huawei.com

Key Words:  Wireless communications, Artificial intelligence, Machine learning


Share this article to: More |Next Article >>>

Jun Wang, Rong Li, Jian Wang, Yi-qun Ge, Qi-fan Zhang, Wu-xian Shi. Artificial intelligence and wireless communications[J]. Frontiers of Information Technology & Electronic Engineering, 2020, 21(10): 1413-1425.

@article{title="Artificial intelligence and wireless communications",
author="Jun Wang, Rong Li, Jian Wang, Yi-qun Ge, Qi-fan Zhang, Wu-xian Shi",
journal="Frontiers of Information Technology & Electronic Engineering",
volume="21",
number="10",
pages="1413-1425",
year="2020",
publisher="Zhejiang University Press & Springer",
doi="10.1631/FITEE.1900527"
}

%0 Journal Article
%T Artificial intelligence and wireless communications
%A Jun Wang
%A Rong Li
%A Jian Wang
%A Yi-qun Ge
%A Qi-fan Zhang
%A Wu-xian Shi
%J Frontiers of Information Technology & Electronic Engineering
%V 21
%N 10
%P 1413-1425
%@ 2095-9184
%D 2020
%I Zhejiang University Press & Springer
%DOI 10.1631/FITEE.1900527

TY - JOUR
T1 - Artificial intelligence and wireless communications
A1 - Jun Wang
A1 - Rong Li
A1 - Jian Wang
A1 - Yi-qun Ge
A1 - Qi-fan Zhang
A1 - Wu-xian Shi
J0 - Frontiers of Information Technology & Electronic Engineering
VL - 21
IS - 10
SP - 1413
EP - 1425
%@ 2095-9184
Y1 - 2020
PB - Zhejiang University Press & Springer
ER -
DOI - 10.1631/FITEE.1900527


Abstract: 
The applications of artificial intelligence (AI) and machine learning (ML) technologies in wireless communications have drawn significant attention recently. AI has demonstrated real success in speech understanding, image identification, and natural language processing domains, thus exhibiting its great potential in solving problems that cannot be easily modeled. AI techniques have become an enabler in wireless communications to fulfill the increasing and diverse requirements across a large range of application scenarios. In this paper, we elaborate on several typical wireless scenarios, such as channel modeling, channel decoding and signal detection, and channel coding design, in which AI plays an important role in wireless communications. Then, AI and information theory are discussed from the viewpoint of the information bottleneck. Finally, we discuss some ideas about how AI techniques can be deeply integrated with wireless communication systems.

人工智能与无线通信

王俊1,李榕1,王坚1,葛屹群2,张其蕃2,史无限2
1华为技术有限公司无线技术实验室,中国杭州市,310051
2华为技术有限公司无线技术实验室,加拿大渥太华市,K0A3M0

摘要:近来,人工智能和机器学习技术在无线通信领域的应用受到极大关注。人工智能在语音理解、图像识别、自然语言处理等领域取得成功,展示了其解决难以建模问题的巨大潜力。无线通信在大量应用场景中存在着日益增长且多样的需求,而人工智能已成为满足这些需求的重要使能技术。本文详细介绍无线通信中人工智能发挥重要作用的一些典型场景,包括信道建模、信道译码和信号检测以及信道编码设计。进而,从信息瓶颈的角度讨论了人工智能和信息论的关系。最后,讨论了将人工智能技术深入集成在无线通信系统的一些想法。

关键词:无线通信;人工智能;机器学习

Darkslateblue:Affiliate; Royal Blue:Author; Turquoise:Article

Reference

[1]Achille A, Soatto S, 2018. Information dropout: learning optimal representations through noisy computation. IEEE Trans Patt Anal Mach Intell, 40(12):2897-2905.

[2]Alemi AA, Fischer I, Dillon JV, et al., 2016. Deep variational information bottleneck. https://arxiv.org/abs/1612.00410

[3]Amjad RA, Geiger BC, 2019. Learning representations for neural network-based classification using the information bottleneck principle. IEEE Trans Patt Anal Mach Intell, in press.

[4]Arikan E, 2011. Systematic polar coding. IEEE Commun Lett, 15(8):860-862.

[5]Arnold M, Dörner S, Cammerer S, et al., 2019. Enabling FDD massive MIMO through deep learning-based channel prediction. https://arxiv.org/abs/1901.03664v1

[6]Barber D, 2012. Bayesian Reasoning and Machine Learning. Cambridge University Press, Cambridge, UK.

[7]Chen X, Duan Y, Houthooft R, et al., 2016. InfoGAN: interpretable representation learning by information maximizing generative adversarial nets. Proc 30th Int Conf on Neural Information Processing Systems, p.2180-2188.

[8]Decurninge A, Ordóñez LG, Ferrand P, et al., 2018. CSI-based outdoor localization for massive MIMO: experiments with a learning approach. Proc 15th Int Symp on Wireless Communication Systems, p.1-6.

[9]Ding TB, Hirose A, 2014. Fading channel prediction based on combination of complex-valued neural networks and chirp Z-transform. IEEE Trans Neur Netw Learn Syst, 25(9):1686-1695.

[10]Estella-Aguerri I, Zaidi A, 2019. Distributed variational representation learning. IEEE Trans Patt Anal Mach Intell, in press.

[11]Farsad N, Goldsmith A, 2017. Detection algorithms for communication systems using deep learning. https://arxiv.org/abs/1705.08044

[12]Grau-Moya J, Leibfried F, Vrancx P, 2018. Soft Q-learning with mutual-information regularization. 7th Int Conf on Learning Representations, p.1-19.

[13]Gruber T, Cammerer S, Hoydis J, et al., 2017. On deep learning-based channel decoding. 51st Annual Conf on Information Sciences and Systems, p.1-6.

[14]Huang LC, Zhang HZ, Li R, et al., 2019. AI coding: learning to construct error correction codes. IEEE Trans Commun, 68(1):26-39.

[15]Huangfu YR, Wang J, Li R, et al., 2019a. Predicting the mumble of wireless channel with sequence-to-sequence models. Proc 30th Annual Int Symp on Personal, Indoor and Mobile Radio Communications, p.1-7.

[16]Huangfu YR, Wang J, Xu C, et al., 2019b. Realistic channel models pre-training. https://arxiv.org/abs/1907.09117

[17]Hur S, Baek S, Kim B, et al., 2016. Proposal on millimeter-wave channel modeling for 5G cellular system. IEEE J Sel Top Signal Process, 10(3):454-469.

[18]Jain RK, Chiu DMW, Hawe WR, 1984. A Quantitative Measure of Fairness and Discrimination for Resource Allocation in Shared Computer System. Technical Report No. DEC-TR-301, Eastern Research Laboratory, Digital Equipment Corporation, Hudson, MA, USA.

[19]Kelly F, 1997. Charging and rate control for elastic traffic. Eur Trans Telecommun, 8(1):33-37.

[20]Kermoal JP, Schumacher L, Pedersen KI, et al., 2002. A stochastic MIMO radio channel model with experimental validation. IEEE J Sel Areas Commun, 20(6):1211-1226.

[21]Kim H, Jiang YH, Rana R, et al., 2018. Communication algorithms via deep learning. https://arxiv.org/abs/1805.09317

[22]Konevčný J, McMahan HB, Yu FX, et al., 2016. Federated learning: strategies for improving communication efficiency. https://arxiv.org/abs/1610.05492

[23]Li B, Shen H, Tse D, 2014. A RM-polar codes. https://arxiv.org/abs/1407.5483

[24]Li YX, 2017. Deep reinforcement learning: an overview. https://arxiv.org/abs/1701.07274

[25]Luo CQ, Ji JL, Wang QL, et al., 2020. Channel state information prediction for 5G wireless communications: a deep learning approach. IEEE Trans Netw Sci Eng, 7(1):227-236.

[26]Luong NC, Hoang DT, Gong SM, et al., 2019. Applications of deep reinforcement learning in communications and networking: a survey. IEEE Commun Surv Tutor, 21(4):3133-3174.

[27]Mao Q, Hu F, Hao Q, 2018. Deep learning for intelligent wireless networks: a comprehensive survey. IEEE Commun Surv Tutor, 20(4):2595-2621.

[28]Mittelstadt B, Russell C, Wachter S, 2019. Explaining explanations in AI. Proc Conf on Fairness, Accountability, and Transparency, p.279-288.

[29]Nachmani E, Be’ery Y, Burshtein D, 2016. Learning to decode linear codes using deep learning. 54th Annual Allerton Conf on Communication, Control, and Computing, p.341-346.

[30]Nachmani E, Marciano E, Lugosch L, et al., 2018. Deep learning methods for improved decoding of linear codes. IEEE J Sel Top Signal Process, 12(1):119-131.

[31]O’Shea T, Hoydis J, 2017. An introduction to deep learning for the physical layer. IEEE Trans Cogn Commun Netw, 3(4):563-575.

[32]Patterson J, Gibson A, 2017. Deep Learning: a Practitioner’s Approach. O’Reilly Media, Inc., Sebastopol, USA.

[33]Qin MH, Guo J, Bhatia A, et al., 2017. Polar code constructions based on LLR evolution. IEEE Commun Lett, 21(6):1221-1224.

[34]Russell S, Norvig P, 2002. Artificial Intelligence: a Modern Approach. Prentice Hall, Upper Saddle River, NJ, USA.

[35]Shannon CE, Weaver W, 1949. The Mathematical Theory of Communication. University of Illinois Press, Urbana, USA.

[36]Shwartz-Ziv R, Tishby N, 2017. Opening the black box of deep neural networks via information. https://arxiv.org/abs/1703.00810

[37]Stampa G, Arias M, Sánchez-Charles D, et al., 2017. A deep-reinforcement learning approach for software-defined networking routing optimization. https://arxiv.org/abs/1709.07080

[38]Sternad M, Aronsson D, 2003. Channel estimation and prediction for adaptive OFDM downlinks [vehicular applications]. Proc 58th Vehicular Technology Conf, p.1283-1287.

[39]Sutskever I, Vinyals O, Le QV, 2014. Sequence to sequence learning with neural networks. Proc 27th Int Conf on Neural Information Processing Systems, p.3104-3112.

[40]Tishby N, Pereira FC, Bialek W, 2000. The information bottleneck method. https://arxiv.org/abs/physics/0004057

[41]Trifonov P, Miloslavskaya V, 2015. Polar subcodes. IEEE J Sel Areas Commun, 34(2):254-266.

[42]Tse D, 2001. Multiuser Diversity in Wireless Networks. Wireless Communications Seminar, Standford University, Stanford, CA, USA.

[43]Vaswani A, Shazeer N, Parmar N, et al., 2017. Attention is all you need. Proc 31st Int Conf on Neural Information Processing Systems, p.6000-6010.

[44]Wang J, Xu C, Huangfu YR, et al., 2019. Deep reinforcement learning for scheduling in cellular networks. Proc 11th Int Conf on Wireless Communications and Signal Processing, p.1-6.

[45]Wang T, Qu DM, Jiang T, 2016. Parity-check-concatenated polar codes. IEEE Commun Lett, 20(12):2342-2345.

[46]Wen CK, Shih WT, Jin S, 2018. Deep learning for massive MIMO CSI feedback. IEEE Wirel Commun Lett, 7(5):748-751.

[47]Xu C, Wang J, Yu TH, et al., 2019. Buffer-aware wireless scheduling based on deep reinforcement learning. https://arxiv.org/abs/1911.05281

[48]Xu ZY, Wang YZ, Tang J, et al., 2017. A deep reinforcement learning based framework for power-efficient resource allocation in cloud RANs. IEEE Int Conf on Communications, p.1-6.

[49]Zappone A, di Renzo M, Debbah M, 2019. Wireless networks design in the era of deep learning: model-based, AI-based, or both? IEEE Trans Commun, 67(10):7331-7376.

[50]Zhang CY, Patras P, Haddadi H, 2019. Deep learning in mobile and wireless networking: a survey. IEEE Commun Surv Tutor, 21(3):2224-2287.

[51]Zhang HZ, Li R, Wang J, et al., 2018. Parity-check polar coding for 5G and beyond. IEEE Int Conf on Communications, p.1-7.

[52]Zhang QS, Zhu SC, 2018. Visual interpretability for deep learning: a survey. Front Inform Technol Electron Eng, 19(1):27-39.

[53]Zhao SJ, Song JM, Ermon S, 2018. The information autoencoding family: a Lagrangian perspective on latent variable generative models. https://arxiv.org/abs/1806.06514

Open peer comments: Debate/Discuss/Question/Opinion

<1>

Please provide your name, email address and a comment





Journal of Zhejiang University-SCIENCE, 38 Zheda Road, Hangzhou 310027, China
Tel: +86-571-87952783; E-mail: cjzhang@zju.edu.cn
Copyright © 2000 - Journal of Zhejiang University-SCIENCE