logo

SCIENTIA SINICA Informationis, Volume 48, Issue 12: 1589-1602(2018) https://doi.org/10.1360/N112018-00174

AI for 5G: research directions and paradigms

More info
  • ReceivedJul 5, 2018
  • AcceptedAug 14, 2018
  • PublishedNov 27, 2018

Abstract

Fifth-generation wireless communication (5G) technologies not only fulfill the requirement of 1000 times increase of Internet traffic in the next decade but also offer the underlying technologies to the entire industry and ecology for the Internet of everything. Compared with the existing mobile communication technologies, 5G technologies are more widely applicable and have more complicated corresponding system design. In order to better balance the complexity and performance, artificial intelligence (AI) technologies have been considered for 5G. Typical and potential research directions to which AI can make promising contributions need to be identified, evaluated, and investigated. To this end, this overview paper first combs through several promising research directions of AI for 5G, based on the understanding of the key aspects of 5G technologies. Furthermore, the paper devotes itself in providing design paradigms including 5G network optimization, optimal resource allocation, 5G physical layer unified acceleration, and end-to-end physical layer joint optimization.


Funded by

国家自然科学基金(61501116,61521061)


References

[1] You X H, Pan Z W, Gao X Q, et al. The 5G mobile communication: the development trends and its emerging key techniques (in Chinese). Sci Sin Inform, 2014, 44: 551--563. Google Scholar

[2] Li L, Wang D, Niu X. mmWave communications for 5G: implementation challenges and advances. Sci China Inf Sci, 2018, 61: 021301 CrossRef Google Scholar

[3] Wang C X, Wu S B, Bai L, et al. Recent advances and future challenges for massive MIMO channel measurements and models. Sci China Inf Sci, 2016, 59: 021301. Google Scholar

[4] Zhang J, Tang P, Tian L. 6-100 GHz research progress and challenges from a channel perspective for fifth generation (5G) and future wireless communication. Sci China Inf Sci, 2017, 60: 080301 CrossRef Google Scholar

[5] Tao X, Han Y, Xu X. Recent advances and future challenges for mobile network virtualization. Sci China Inf Sci, 2017, 60: 040301 CrossRef Google Scholar

[6] Way forward on the overall 5G-NR eMBB. Workplan RP-170741. 2017. ftp://ftp.3gpp.org/TSG RAN/TSG RAN/TSGR 75/Docs/RP-170741.zip. Google Scholar

[7] Study on new radio access technology: radio access architecture and interfaces (release 14). TR38.801, v14.0. 2017. http://www.3gpp.org/ftp/Specs/archive/38 series/38.801/38801-e00.zip. Google Scholar

[8] ITU-R. Minimum requirements related to technical performance for IMT2020 radio interface(s). Report ITU-R M.2410-0. 2017. https://www.itu.int/pub/R-REP-M.2410-2017. Google Scholar

[9] LTE Enhancements and 5G Normative Work. Release-15. 2018. http://www.3gpp.org/release-15. Google Scholar

[10] You X H, Wang D M, Sheng B. Cooperative distributed antenna systems for mobile communications [Coordinated and Distributed MIMO. IEEE Wireless Commun, 2010, 17: 35-43 CrossRef Google Scholar

[11] Yang W, Wang M, Zhang J. Narrowband Wireless Access for Low-Power Massive Internet of Things: A Bandwidth Perspective. IEEE Wireless Commun, 2017, 24: 138-145 CrossRef Google Scholar

[12] ITU-T. LS/o on the results of the 1st meeting of the ITU-T focus group on ma- chine learning for future networks including 5G (FG ML5G). FG ML5G-0-004. 2018. http://www.3gpp.org/ftp/tsg sa/WG1 Serv/TSGS1 82 Dubrovnik/Docs/S1-181271.zip. Google Scholar

[13] 5G system network data analytics services stage 3. TS 29.520 (CT3). 2018. http://www.etsi.org/deliver/etsi ts/129500 129599/129520/15.00.00 60/ts 129520v150000p.pdf. Google Scholar

[14] Whitley D. A genetic algorithm tutorial. Stat Comput, 1994, 4: 65--85. Google Scholar

[15] Schmidhuber J. Deep learning in neural networks: an overview.. Neural Networks, 2015, 61: 85-117 CrossRef PubMed Google Scholar

[16] Xiao-Hu Yu , Guo-An Chen , Shi-Xin Cheng . Dynamic learning rate optimization of the backpropagation algorithm.. IEEE Trans Neural Netw, 1995, 6: 669-677 CrossRef PubMed Google Scholar

[17] Yu X H. Can backpropagation error surface not have local minima.. IEEE Trans Neural Netw, 1992, 3: 1019-1021 CrossRef PubMed Google Scholar

[18] Yu X H, Chen G A. Efficient Backpropagation Learning Using Optimal Learning Rate and Momentum. Neural Networks, 1997, 10: 517-527 CrossRef Google Scholar

[19] Kaelbling L P, Littman M L, Moore A W. Reinforcement Learning: A Survey. jair, 1996, 4: 237-285 CrossRef Google Scholar

[20] Watkins C J C H, Dayan P. Q-learning. Mach Learn, 1992, 8: 279--292. Google Scholar

[21] Finn C, Abbeel P, Levine S. Model-agnostic meta-learning for fast adaptation of deep networks. 2017,. arXiv Google Scholar

[22] Wu J, Gao B B, Wei X S. Resource-constrained deep learning: challenges and practices. Sci Sin-Inf, 2018, 48: 501-510 CrossRef Google Scholar

[23] Zhou Z H. Machine learning: recent progress in China and beyond. China Sci Rev, 2018, 5: 20. Google Scholar

[24] Zhong Y X. Artificial intelligence: Concept, approach and opportunity. Chin Sci Bull, 2017, 62: 2473-2479 CrossRef Google Scholar

[25] Gatherer A. Machine learning Modems: how ML will change how we specify and design next generation communication systems. IEEE ComSoc Tech News, 2018. https://www.comsoc.org/ctn/machine-learning-modems-how-ml-will-change-how-we-specify-and-design-next-generation. Google Scholar

[26] Yang C, Xu W H, Zhang Z C, et al. A channel-blind detection for SCMA based on image processing techniques. In: Proceedings of IEEE International Symposium on Circuits and Systems (ISCAS), 2018. 1--5. Google Scholar

[27] Zhang C, Xu W H. Neural networks: efficient implementations and applications. In: Proceedings of IEEE International Conference on ASIC (ASICON), 2017. 1029--1032. Google Scholar

[28] Xu W H, You X H, Zhang C. Efficient deep convolutional neural networks accelerator without multiplication and retraining. In: Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2018. 1--5. Google Scholar

[29] Xu W H, Wang Z F, You X H, et al. Efficient fast convolution architectures for convolutional neural network. In: Proceedings of IEEE International Conference on ASIC (ASICON), 2017. 904--907. Google Scholar

[30] Xu W H, Wu Z Z, Ueng Y L, et al. Improved polar decoder based on deep learning. In: Proceedings of IEEE International Workshop on Signal Processing Systems (SiPS), 2017. 1--6. Google Scholar

[31] Xu W H, Zhong Z W, Be'ery Y, et al. Joint neural network equalizer and decoder. In: Proceedings of IEEE International Symposium on Wireless Communication Systems (ISWCS), 2018. 1--6. Google Scholar

[32] Xu W H, Be'ery Y, You X H, et al. Polar decoding on sparse graphs with deep learning. In: Proceedings of Asilomar Conference on Signals, Systems, and Computers (Asilomar), 2018. 1--6. Google Scholar

[33] Xu W H, You X H, Zhang C. Using Fermat number transform to accelerate convolutional neural network. In: Proceedings of IEEE International Conference on ASIC (ASICON), 2017. 1033--1036. Google Scholar

[34] Gomez-Andrades A, Munoz P, Serrano I. Automatic Root Cause Analysis for LTE Networks Based on Unsupervised Techniques. IEEE Trans Veh Technol, 2016, 65: 2369-2386 CrossRef Google Scholar

[35] Liang F, Shen C, Wu F. An Iterative BP-CNN Architecture for Channel Decoding. IEEE J Sel Top Signal Process, 2018, 12: 144-159 CrossRef ADS arXiv Google Scholar

[36] Lv X Z, Wei P, Xiao X C. Automatic identification of digital modulation signals using high order cumulants. Electronic Warfare, 2004, 6: 1. Google Scholar

[37] Wang T, Wen C K, Wang H. Deep learning for wireless physical layer: Opportunities and challenges. China Commun, 2017, 14: 92-111 CrossRef Google Scholar

[38] Gao X, Jiang B, Li X. Statistical Eigenmode Transmission Over Jointly Correlated MIMO Channels. IEEE Trans Inform Theor, 2009, 55: 3735-3750 CrossRef Google Scholar

[39] Wang D, Zhang Y, Wei H. An overview of transmission theory and techniques of large-scale antenna systems for 5G wireless communications. Sci China Inf Sci, 2016, 59: 081301 CrossRef Google Scholar

[40] Gesbert D, Hanly S, Huang H. Multi-cell MIMO cooperative networks: A new look at interference. IEEE J Sel Areas Commun, 2010, 28: 1380-1408 CrossRef Google Scholar

[41] Jing S S, Yu A L, Liang X, et al. Uniform belief propagation processor for massive MIMO detection and GF (2$^{n}$) LDPC decoding. In: Proceedings of IEEE International Conference on ASIC (ASICON), 2017. 961--964. Google Scholar

[42] Gandhi V S, Maheswaran B. A cross layer design for performance enhancements in LTE-A system. In: Proceedings of IEEE International Conference on Wireless Communications, Signal Processing and Networking (WiSPNET), 2016. 905--909. Google Scholar

[43] Kuen J, Kong X F, Wang G, et al. DelugeNets: deep networks with efficient and flexible cross-layer information inflows. In: Proceedings of IEEE International Conference on Computer Vision Workshop (ICCVW), 2017. 958--966. Google Scholar

[44] Farsad N, Rao M, Goldsmith A. Deep learning for joint source-channel coding of text. 2018,. arXiv Google Scholar

[45] Xu X, Ding Y, Hu S X. Scaling for edge inference of deep neural networks. Nat Electron, 2018, 1: 216-222 CrossRef Google Scholar

[46] Wang X, Li X, Leung V C M. Artificial Intelligence-Based Techniques for Emerging Heterogeneous Network: State of the Arts, Opportunities, and Challenges. IEEE Access, 2015, 3: 1379-1391 CrossRef Google Scholar

[47] Klaine P V, Imran M A, Onireti O. A Survey of Machine Learning Techniques Applied to Self-Organizing Cellular Networks. IEEE Commun Surv Tutorials, 2017, 19: 2392-2431 CrossRef Google Scholar

[48] Pèrez-Romero J, Sallent O, Ferrús R, et al. Knowledge-based 5G radio access network planning and optimization. In: Proceedings of IEEE International Symposium on Wireless Communication Systems (ISWCS), 2016. 359--365. Google Scholar

[49] Wang J, Guan W, Huang Y. Distributed Optimization of Hierarchical Small Cell Networks: A GNEP Framework. IEEE J Sel Areas Commun, 2017, 35: 249-264 CrossRef Google Scholar

[50] Bogale T E, Wang X, Le L B. Machine intelligence techniques for next-generation context-aware wireless networks. 2018,. arXiv Google Scholar

[51] Li R, Zhao Z, Zhou X. Intelligent 5G: When Cellular Networks Meet Artificial Intelligence. IEEE Wireless Commun, 2017, 24: 175-183 CrossRef Google Scholar

[52] Zhao Z, Li R, Sun Q, et al. Deep reinforcement learning for network slicing. 2018,. arXiv Google Scholar

[53] Ren Y R, Zhang C, Liu X, et al. Efficient early termination schemes for belief-propagation decoding of polar codes. In: Proceedings of IEEE International Conference on ASIC (ASICON), 2015. 1--4. Google Scholar

[54] Fossorier M P C, Mihaljevic M, Imai H. Reduced complexity iterative decoding of low-density parity check codes based on belief propagation. IEEE Trans Commun, 1999, 47: 673-680 CrossRef Google Scholar

[55] Yang J, Song W, Zhang S. Low-Complexity Belief Propagation Detection for Correlated Large-Scale MIMO Systems. J Sign Process Syst, 2018, 90: 585-599 CrossRef Google Scholar

[56] Liu L, Yuen C, Guan Y L, et al. Gaussian message passing iterative detection for MIMO-NOMA systems with massive access. In: Proceedings of IEEE Global Communications Conference (GLOBECOM), 2016. 1--6. Google Scholar

[57] Yang J M, Zhang C, Zhou H Y, et al. Pipelined belief propagation polar decoders. In: Proceedings of IEEE International Symposium on Circuits and Systems (ISCAS), 2016. 413--416. Google Scholar

[58] Tan X S, Xu W H, Be'ery Y, et al. Improving massive MIMO belief propagation detector with deep neural network. 2018,. arXiv Google Scholar

[59] O'Shea T, Hoydis J. An Introduction to Deep Learning for the Physical Layer. IEEE Trans Cogn Commun Netw, 2017, 3: 563-575 CrossRef Google Scholar

[60] O'Shea T J, Erpek T, Clancy T C. Deep learning based MIMO communications. 2017,. arXiv Google Scholar

Copyright 2019 Science China Press Co., Ltd. 《中国科学》杂志社有限责任公司 版权所有

京ICP备18024590号-1