人工智能在5G系统中的应用综述

doi:10.11959/j.issn.1000-0801.2021109

电信科学 ›› 2021, Vol. 37 ›› Issue (5): 14-31.doi: 10.11959/j.issn.1000-0801.2021109

• 专题：通信与AI融合 • 上一篇下一篇

人工智能在5G系统中的应用综述

章坚武¹, 王路鑫¹, 孙玲芬², 章谦骅³^,⁴, 单杭冠⁴

¹ 杭州电子科技大学，浙江杭州 310018
² 英国普利茅斯大学，英国普利茅斯 PL48AA
³ 之江实验室智能网络研究中心，浙江杭州311121
⁴ 浙江大学，浙江杭州 310007

修回日期:2020-05-15 出版日期:2021-05-20 发布日期:2021-05-01
作者简介:章坚武（1961− ），男，博士，杭州电子科技大学通信工程学院教授、博士生导师，中国电子学会、中国通信学会高级会员，浙江省通信学会常务理事，主要研究方向为移动通信、多媒体信号处理与人工智能、通信网络与信息安全
王路鑫（1996− ），男，杭州电子科技大学通信工程学院硕士生，主要研究方向为 5G接入边缘计算等
孙玲芬（1963− ），女，博士，英国普利茅斯大学副教授，英国高等教育学会会士，主要研究方向为多媒体和网络质量评估、QoS/QoE管理与控制、VoIP等
章谦骅（1990− ），男，浙江大学博士生，之江实验室智能网络研究中心工程师，主要研究方向为无线网络、物联网、智慧城市等
单杭冠（1982− ），男，浙江大学副教授、博士生导师，主要研究方向为与5G移动通信相关的网络设计和QoS保障等
基金资助:
国家自然科学基金资助项目(U1866209);国家自然科学基金资助项目(61772162);英国皇家学会国际合作交流项目(IEC\NSFC\181300)

An survey on application of artificial intelligence in 5G system

Jianwu ZHANG¹, Luxin WANG¹, Lingfen SUN², Qianye ZHANG³^,⁴, Hangguan SHAN⁴

¹ Hangzhou Dianzi University, Hangzhou 310018, China
² University of Plymouth, Plymouth PL48AA, UK
³ Research Center for Intelligent Network, Zhejiang Lab, Hangzhou 311121, China
⁴ Zhejiang University, Hangzhou 310007, China

Revised:2020-05-15 Online:2021-05-20 Published:2021-05-01
Supported by:
The National Natural Science Foundation of China(U1866209);The National Natural Science Foundation of China(61772162);The Royal Society, International Exchanges 2018 Cost Share (China) Grant(IEC\NSFC\181300)

摘要/Abstract

摘要：

随着5G的不断发展，万物互联时代即将来临。海量设备连接、海量业务请求、超高网络负载、复杂动态的网络环境等对5G系统优化提出了巨大的挑战。面对这些技术难点，人工智能（AI）算法表现了其独特的优势。首先对5G系统中基于深度学习的AI算法相比于传统算法的优势进行介绍；随后，针对多接入边缘计算和毫米波大规模多输入多输出（mmWave massive MIMO）系统中的AI算法应用进行详细的阐述，并对比分析了各种方法的优劣；最后，根据已有研究，总结了AI算法在5G实际场景中存在的不足，并对未来研究方向提出了展望。

关键词: 5G, 人工智能, 强化学习, 边缘计算, 毫米波大规模MIMO

Abstract:

With the continuous development of 5G, the era of the internet of everything is coming.Problems such as massive device connections, massive application requests, ultra-high network load and complex dynamic network environment pose great challenges to the optimization of 5G systems in the context of the internet of everything.Facing these challenges, artificial intelligence (AI) shows its unique advantages.Firstly, the advantages of deep learning driven AI algorithms in 5G system compared with conventional algorithms were briefly introduced.Then, the application of AI algorithms in multi-access edge computing (MEC) and mmWave massive multiple-input multiple-output (MIMO) system were described in detail, with advantages and disadvantages of each method being compared and analyzed.Finally, according to the existing research, the shortcomings of AI algorithms in 5G application scenarios were summarized and the future research directions were forecasted.

Key words: 5G, artificial intelligence, reinforcement learning, edge computing, mmWave massive MIMO

中图分类号:

TN929

章坚武, 王路鑫, 孙玲芬, 章谦骅, 单杭冠. 人工智能在5G系统中的应用综述[J]. 电信科学, 2021, 37(5): 14-31.

Jianwu ZHANG, Luxin WANG, Lingfen SUN, Qianye ZHANG, Hangguan SHAN. An survey on application of artificial intelligence in 5G system[J]. Telecommunications Science, 2021, 37(5): 14-31.

图/表 10

表1

图1

图2

图3

图4

图5

图6

表2

各网络NMSE性能对比（单位：dB）"

	压缩率（CR）	CsiNet^[67]	CsiNet+^[68]	SM-CsiNet+^[68]	PM-CsiNet+^[68]	LSTM-CsiNet^[68]
室内	4	-17.36	-27.37	$- 27 . 90$	-27.60	—
	8	-12.70	-18.29	$- 18 . 49$	-17.70	—
	16	-8.64	-14.14	-13.45	-12.25	$- 23 . 06$
	32	-6.24	-10.43	-9.89	-8.24	$- 22 . 33$
	64	-5.84	—	—	—	$- 21 . 24$
室外	4	-8.75	$- 12 . 40$	-11.91	-12.02	—
	8	-7.61	$- 8 . 72$	-8.25	-8.10	—
	16	-4.51	-5.73	-5.31	-5.07	$- 9 . 86$
	32	-2.81	-3.4	-3.22	-3.00	$- 9 . 18$
	64	-1.93	—	—	—	$- 8 . 83$

表2

表3

表4

参考文献 88

[1]	GHOSH A , MAEDER A , BAKER M ,et al. 5G evolution: a view on 5G cellular technology beyond 3GPP release 15[J]. IEEE Access, 2019(7): 127639-127651.
[2]	ZHANG C , HUANG Y H , SHEIKH F ,et al. Advanced baseband processing algorithms,circuits,and implementations for 5G communication[J]. IEEE Journal on Emerging and Selected Topics in Circuits and Systems, 2017,7(4): 477-490.
[3]	MA Z , ZHANG Z Q , DING Z G ,et al. Key techniques for 5G wireless communications: network architecture,physical layer,and MAC layer perspectives[J]. Science China Information Sciences, 2015,58(4): 1-20.
[4]	LIN C Z , LU J W , WANG G ,et al. Graininess-aware deep feature learning for robust pedestrian detection[J]. IEEE Transactions on Image Processing, 2020(29): 3820-3834.
[5]	ZHU S , CAO R S , YU K . Dual learning for semi-supervised natural language understanding[J]. IEEE/ACM Transactions on Audio,Speech,and Language Processing, 2020(28): 1936-1947.
[6]	SYNNAEVE G , BESSIèRE P . Multiscale Bayesian modeling for RTS games: an application to StarCraft AI[J]. IEEE Transactions on Computational Intelligence and AI in Games, 2016,8(4): 338-350.
[7]	刘留, 张建华, 樊圆圆 ,等. 机器学习在信道建模中的应用综述[J]. 通信学报, 2021,42(2): 134-153.
	LIU L , ZHANG J H , FAN Y Y ,et al. Survey of application of machine learning in wireless channel modeling[J]. Journal on Communications, 2021,42(2): 134-153.
[8]	尤肖虎, 张川, 谈晓思 ,等. 基于AI的5G技术: 研究方向与范例[J]. 中国科学: 信息科学, 2018,48(12): 1589-1602.
	YOU X H , ZHANG C , TAN X S ,et al. AI for 5G: research directions and paradigms[J]. Scientia Sinica (Informationis), 2018,48(12): 1589-1602.
[9]	张建敏, 杨峰义, 武洲云 . 多接入边缘计算（MEC）及关键技术[M]. 北京: 人民邮电出版社, 2019.
	ZHANG J M , YANG F Y , WU Z Y . Multi-access edge compu-ting (MEC) and key technologies[M]. Beijing: Posts ＆ Telecom Press, 2019.
[10]	NING Z L , HU X P , CHEN Z K ,et al. A cooperative quality-aware service access system for social Internet of vehicles[J]. IEEE Internet of Things Journal, 2020,7(7): 6663.
[11]	谢人超, 廉晓飞, 贾庆民 ,等. 移动边缘计算卸载技术综述[J]. 通信学报, 2018,39(11): 138-155.
	XIE R C , LIAN X F , JIA Q M ,et al. Survey on computation of-floading in mobile edge computing[J]. Journal on Communica-tions, 2018,39(11): 138-155.
[12]	陈山枝, 王胡成, 时岩 . 5G移动性管理技术[M]. 北京: 人民邮电出版社, 2019.
	CHEN S Z , WANG H C , SHI Y . Mobile management technol-ogy for 5G[M]. Beijing: Posts ＆ Telecom Press, 2019.
[13]	杨志强, 粟栗, 杨波 ,等. 5G 安全技术与标准[M]. 北京: 人民邮电出版社, 2020.
	YANG Z Q , SU L , YANG B ,et al. 5G security technologies and standards[M]. Beijing: Posts ＆ Telecom Press, 2020.
[14]	CAO Z L , ZHOU P , LI R X ,et al. Multiagent deep reinforcement learning for joint multichannel access and task offloading of mobile-edge computing in industry 4.0[J]. IEEE Internet of Things Journal, 2020,7(7): 6201-6213.
[15]	WU H M , ZHANG Z R , GUAN C ,et al. Collaborate edge and cloud computing with distributed deep learning for smart city Internet of Things[J]. IEEE Internet of Things Journal, 2020,7(9): 8099-8110.
[16]	YANG B , CAO X L , LI X F ,et al. Mobile-edge- computing-based hierarchical machine learning tasks distribution for IIoT[J]. IEEE Internet of Things Journal, 2020,7(3): 2169-2180.
[17]	YANG B , CAO X L , LI X F ,et al. Joint communication and computing optimization for hierarchical machine learning tasks distribution[C]// Proceedings of 2019 IEEE Symposium on Computers and Communications (ISCC). Piscataway: IEEE Press, 2019: 1-6.
[18]	JIANG F B , WANG K Z , DONG L ,et al. Stacked autoencoder-based deep reinforcement learning for online resource scheduling in large-scale MEC networks[J]. IEEE Internet of Things Journal, 2020,7(10): 9278-9290.
[19]	NATH S , LI Y Z , WU J X ,et al. Multi-user multi-channel computation offloading and resource allocation for mobile edge computing[C]// Proceedings of ICC 2020 - 2020 IEEE International Conference on Communications (ICC). Piscataway: IEEE Press, 2020: 1-6.
[20]	HUANG L , BI S Z , ZHANG Y J A . Deep reinforcement learning for online computation offloading in wireless powered mobile-edge computing networks[J]. IEEE Transactions on Mobile Computing, 2020,19(11): 2581-2593.
[21]	SONG X , CHAI R , CHEN Q B . Joint task offloading,CNN layer scheduling and resource allocation in cooperative computing system[C]// Proceedings of Communications and Networking.[S.l.:s.n.], 2020.
[22]	LI J , GAO H , LV T ,et al. Deep reinforcement learning based computation offloading and resource allocation for MEC[C]// Proceedings of 2018 IEEE Wireless Communications and Networking Conference (WCNC). Piscataway:IEEE Press, 2018: 1-6.
[23]	赵海涛, 张唐伟, 陈跃 ,等. 基于DQN的车载边缘网络任务分发卸载算法[J]. 通信学报, 2020,41(10): 172-178.
	ZHAO H T , ZHANG T W , CHEN Y ,et al. Task distribution offloading algorithm of vehicle edge network based on DQN[J]. Journal on Communications, 2020,41(10): 172-178.
[24]	MACH P , BECVAR Z . Cloud-aware power control for cloud-enabled small cells[C]// Proceedings of 2014 IEEE Globecom Workshops (GC Wkshps). Piscataway:IEEE Press, 2014: 1038-1043.
[25]	WANG S Q , ZAFER M , LEUNG K K . Online placement of multi-component applications in edge computing environments[J]. IEEE Access, 2017(5): 2514-2533.
[26]	ALI Z , KHAF S , ABBAS Z H ,et al. A deep learning approach for mobility-aware and energy-efficient resource allocation in MEC[J]. IEEE Access, 2020(8): 179530-179546.
[27]	DIN N , CHEN H P , KHAN D . Mobility-aware resource allocation in multi-access edge computing using deep reinforcement learning[C]// Proceedings of 2019 IEEE Intl Conf on Parallel ＆Distributed Processing with Applications,Big Data ＆ Cloud Computing,Sustainable Computing ＆ Communications,Social Computing ＆ Networking. Piscataway:IEEE Press, 2019: 202-209.
[28]	ZHAN W H , LUO C B , WANG J ,et al. Deep-reinforcementlearning-based offloading scheduling for vehicular edge computing[J]. IEEE Internet of Things Journal, 2020,7(6): 5449-5465.
[29]	SCHULMAN J , WOLSKI F , DHARIWAL P ,et al. Proximal policy optimization algorithms[EB]. 2017.
[30]	WU C L , CHIU T C , WANG C Y ,et al. Mobility-aware deep reinforcement learning with glimpse mobility prediction in edge computing[C]// Proceedings of ICC 2020 - 2020 IEEE International Conference on Communications (ICC). Piscataway: IEEE Press, 2020: 1-7.
[31]	WANG J F , LV T , HUANG P M ,et al. Mobility-aware partial computation offloading in vehicular networks: a deep reinforcement learning based scheme[J]. China Communications, 2020,17(10): 31-49.
[32]	ABBAS N , ZHANG Y , TAHERKORDI A ,et al. Mobile edge computing: a survey[J]. IEEE Internet of Things Journal, 2018,5(1): 450-465.
[33]	杨建喜, 张媛利, 蒋华 ,等. 边缘计算中基于深度 Q 网络的物理层假冒攻击检测方法[J]. 计算机应用, 2020,40(11): 3229-3235.
	YANG J X , ZHANG Y L , JIANG H ,et al. Detection method of physical-layer impersonation attack based on deep Q-network in edge computing[J]. Journal of Computer Applications, 2020,40(11): 3229-3235.
[34]	陈佳, 欧阳金源, 冯安琪 ,等. 边缘计算构架下基于孤立森林算法的 DoS 异常检测[J]. 计算机科学, 2020,47(2): 287-293.
	CHEN J , OUYANG J Y , FENG A Q ,et al. DoS anomaly detec-tion based on isolation forest algorithm under edge computing framework[J]. Computer Science, 2020,47(2): 287-293.
[35]	GOPALAKRISHNAN T , RUBY D , AL-TURJMAN F ,et al. Deep learning enabled data offloading with cyber attack detection model in mobile edge computing systems[J]. IEEE Access, 2020(8): 185938-185949.
[36]	KAYODE O , TOSUN A S . Deep Q-network for enhanced data privacy and security of IoT traffic[C]// Proceedings of 2020 IEEE 6th World Forum on Internet of Things (WF-IoT). Piscataway: IEEE Press, 2020: 1-6.
[37]	XIONG J B , ZHAO M F , BHUIYAN M Z A ,et al. An AI-enabled three-party game framework for guaranteed data privacy in mobile edge crowdsensing of IoT[J]. IEEE Transactions on Industrial Informatics, 2021,17(2): 922-933.
[38]	HE X F , JIN R C , DAI H Y . Deep PDS-learning for privacy-aware offloading in MEC-enabled IoT[J]. IEEE Internet of Things Journal, 2019,6(3): 4547-4555.
[39]	DONG J Y , GENG D Q , HE X F . Privacy-aware task offloading via two-timescale reinforcement learning[C]// Proceedings of 2020 IEEE/CIC International Conference on Communications in China (ICCC). Piscataway: IEEE Press, 2020: 220-225.
[40]	CHEN S G , YOU Z H , RUAN X K . Privacy and energy co-aware data aggregation computation offloading for fog-assisted IoT networks[J]. IEEE Access, 2020(8): 72424-72434.
[41]	HUANG B B , LI Z J , TANG P ,et al. Security modeling and efficient computation offloading for service workflow in mobile edge computing[J]. Future Generation Computer Systems, 2019,97: 755-774.
[42]	CHEN T , MATINMIKKO M , CHEN X F ,et al. Software defined mobile networks:concept,survey,and research directions[J]. IEEE Communications Magazine, 2015,53(11): 126-133.
[43]	BUSARI S A , HUQ K M S , MUMTAZ S ,et al. Millimeter-wave massive MIMO communication for future wireless systems: a survey[J]. IEEE Communications Surveys ＆ Tutorials, 2018,20(2): 836-869.
[44]	LI Q C , NIU H N , PAPATHANASSIOU A T ,et al. 5G network capacity: key elements and technologies[J]. IEEE Vehicular Technology Magazine, 2014,9(1): 71-78.
[45]	UWAECHIA A N , MAHYUDDIN N M . A comprehensive survey on millimeter wave communications for fifth-generation wireless networks: feasibility and challenges[J]. IEEE Access, 2020(8): 62367-62414.
[46]	AYACH O E , RAJAGOPAL S , ABU-SURRA S ,et al. Spatially sparse precoding in millimeter wave MIMO systems[J]. IEEE Transactions on Wireless Communications, 2014,13(3): 1499-1513.
[47]	YU X H , SHEN J C , ZHANG J ,et al. Alternating minimization algorithms for hybrid precoding in millimeter wave MIMO systems[J]. IEEE Journal of Selected Topics in Signal Processing, 2016,10(3): 485-500.
[48]	CHEN C E . An iterative hybrid transceiver design algorithm for millimeter wave MIMO systems[J]. IEEE Wireless Communications Letters, 2015,4(3): 285-288.
[49]	JIN J N , ZHENG Y R , CHEN W ,et al. Hybrid precoding for millimeter wave MIMO systems: a matrix factorization approach[J]. IEEE Transactions on Wireless Communications, 2018,17(5): 3327-3339.
[50]	ALKHATEEB A , LEUS G , HEATH R W . Limited feedback hybrid precoding for multi-user millimeter wave systems[J]. IEEE Transactions on Wireless Communications, 2015,14(11): 6481-6494.
[51]	NI W H , DONG X D . Hybrid block diagonalization for massive multiuser MIMO systems[J]. IEEE Transactions on Communications, 2016,64(1): 201-211.
[52]	LIANG L , XU W , DONG X D . Low-complexity hybrid precoding in massive multiuser MIMO systems[J]. IEEE Wireless Communications Letters, 2014,3(6): 653-656.
[53]	DAI L L , GAO X Y , QUAN J G ,et al. Near-optimal hybrid analog and digital precoding for downlink mmWave massive MIMO systems[C]// Proceedings of 2015 IEEE International Conference on Communications (ICC). Piscataway: IEEE Press, 2015: 1334-1339.
[54]	GAO X Y , DAI L L , HAN S F ,et al. Energy-efficient hybrid analog and digital precoding for mmWave MIMO systems with large antenna arrays[J]. IEEE Journal on Selected Areas in Communications, 2016,34(4): 998-1009.
[55]	YU X H , ZHANG J , LETAIEF K B . A hardware-efficient analog network structure for hybrid precoding in millimeter wave systems[J]. IEEE Journal of Selected Topics in Signal Processing, 2018,12(2): 282-297.
[56]	PARK S , ALKHATEEB A , HEATH R W . Dynamic subarrays for hybrid precoding in wideband mmWave MIMO systems[J]. IEEE Transactions on Wireless Communications, 2017,16(5): 2907-2920.
[57]	JING X R , LI L H , LIU H Q ,et al. Dynamically connected hybrid precoding scheme for millimeter-wave massive MIMO systems[J]. IEEE Communications Letters, 2018,22(12): 2583-2586.
[58]	PAYAMI S , GHORAISHI M , DIANATI M . Hybrid beamforming for large antenna arrays with phase shifter selection[J]. IEEE Transactions on Wireless Communications, 2016,15(11): 7258-7271.
[59]	SIDHARTH C , HIREMATH S M , PATRA S K . Deep Learning based Hybrid Precoding for mmWave Massive MIMO system using ComcepNet[C]// Proceedings of 2020 International Conference on Communication and Signal Processing (ICCSP). Piscataway: IEEE Press, 2020: 1317-1321.
[60]	HUANG H J , SONG Y W , YANG J ,et al. Deep-learning-based millimeter-wave massive MIMO for hybrid precoding[J]. IEEE Transactions on Vehicular Technology, 2019,68(3): 3027-3032.
[61]	CHAI M Y , TANG S H , ZHAO M ,et al. HPNet: a compressed neural network for robust hybrid precoding in multi-user massive MIMO systems[C]// Proceedings of GLOBECOM 2020 2020 IEEE Global Communications Conference. Piscataway:IEEE Press, 2020: 1-7.
[62]	MA W Y , QI C H , ZHANG Z C ,et al. Sparse channel estimation and hybrid precoding using deep learning for millimeter wave massive MIMO[J]. IEEE Transactions on Communications, 2020,68(5): 2838-2849.
[63]	MIR T , ZAIN SIDDIQI M , MIR U ,et al. Machine learning inspired hybrid precoding for wideband millimeter-wave massive MIMO systems[J]. IEEE Access, 2019(7): 62852-62864.
[64]	JIANG J , YANG Y . Deep learning assisted hybrid precoding with dynamic subarrays in mmWave MU-MIMO system[C]// Proceedings of 2020 IEEE/CIC International Conference on Communications in China (ICCC). Piscataway: IEEE Press, 2020: 256-261.
[65]	BAO X L , FENG W J , ZHENG J L ,et al. Deep CNN and equivalent channel based hybrid precoding for mmWave massive MIMO systems[J]. IEEE Access, 2020(8): 19327-19335.
[66]	甘天江, 傅友华, 王海荣 . 毫米波大规模 MIMO 系统中基于机器学习的自适应连接混合预编码[J]. 信号处理, 2020,36(5): 677-685.
	GAN T J , FU Y H , WANG H R . Machine learning-based adap-tive connection hybrid precoding for mmWave massive MIMO systems[J]. Journal of Signal Processing, 2020,36(5): 677-685.
[67]	LI J L , ZHANG Q , XIN X J ,et al. Deep learning-based massive MIMO CSI feedback[C]// Proceedings of 2019 18th International Conference on Optical Communications and Networks (ICOCN). Piscataway: IEEE Press, 2019: 1-3.
[68]	GUO J J , WEN C K , JIN S ,et al. Convolutional neural network-based multiple-rate compressive sensing for massive MIMO CSI feedback:design,simulation,and analysis[J]. IEEE Transactions on Wireless Communications, 2020,19(4): 2827-2840.
[69]	WANG T Q , WEN C K , JIN S ,et al. Deep learning-based CSI feedback approach for time-varying massive MIMO channels[J]. IEEE Wireless Communications Letters, 2019,8(2): 416-419.
[70]	LI Q , ZHANG A H , LIU P C ,et al. A novel CSI feedback approach for massive MIMO using LSTM-attention CNN[J]. IEEE Access, 2020(8): 7295-7302.
[71]	KARIM F , MAJUMDAR S , DARABI H ,et al. LSTM fully convolutional networks for time series classification[J]. IEEE Access, 2018(6): 1662-1669.
[72]	LIU Z Y , ZHANG L , DING Z . An efficient deep learning framework for low rate massive MIMO CSI reporting[J]. IEEE Transactions on Communications, 2020,68(8): 4761-4772.
[73]	LIU Z Y , ZHANG L , DING Z . Exploiting Bi-directional channel reciprocity in deep learning for low rate massive MIMO CSI feedback[J]. IEEE Wireless Communications Letters, 2019,8(3): 889-892.
[74]	CHEN T , GUO J J , JIN S ,et al. A novel quantization method for deep learning-based massive MIMO CSI feedback[C]// Proceedings of 2019 IEEE Global Conference on Signal and Information Processing (GlobalSIP). Piscataway: IEEE Press, 2019: 1-5.
[75]	SUN Y Y , XU W , FAN L S ,et al. AnciNet: an efficient deep learning approach for feedback compression of estimated CSI in massive MIMO systems[J]. IEEE Wireless Communications Letters, 2020,9(12): 2192-2196.
[76]	SAMUEL S , KRISTOPHER H , JUN G ,et al. Marefat,Tamal Bose:machine learning based MIMO equalizer for high frequency (HF) communications[Z]. 2020.
[77]	CARRERA D F , VARGAS-ROSALES C , YUNGAICELA-NAULA N M ,et al. Comparative study of artificial neural network based channel equalization methods for mmWave communications[J]. IEEE Access, 2021(9): 41678-41687.
[78]	ZHANG Y , DOSHI A , LISTON R ,et al. DeepWiPHY: deep learning-based receiver design and dataset for IEEE 802.11ax systems[J]. IEEE Transactions on Wireless Communications, 2021,20(3): 1596-1611.
[79]	YE H , LI G Y . Initial results on deep learning for joint channel equalization and decoding[C]// Proceedings of 2017 IEEE 86th Vehicular Technology Conference (VTC-Fall). Piscataway:IEEE Press, 2017: 1-5.
[80]	NWANKWO C D , ZHANG L , QUDDUS A ,et al. A survey of self-interference management techniques for single frequency full duplex systems[J]. IEEE Access, 2018(6): 30242-30268.
[81]	GUO H Q , WU S E , WANG H G ,et al. DSIC: deep learning based self-interference cancellation for in-band full duplex wireless[C]// Proceedings of 2019 IEEE Global Communications Conference (GLOBECOM). Piscataway: IEEE Press, 2019: 1-6.
[82]	CHEN Y T , MISHRA R K , SCHWARTZ D ,et al. MIMO full duplex radios with deep learning[C]// Proceedings of 2020 IEEE International Conference on Communications Workshops (ICC Workshops). Piscataway: IEEE Press, 2020: 1-6.
[83]	GUO H Q , XU J H , ZHU S Y ,et al. Realtime software defined self-interference cancellation based on machine learning for in-band full duplex wireless communications[C]// Proceedings of 2018 International Conference on Computing,Networking and Communications (ICNC). Piscataway:IEEE Press, 2018: 779-783.
[84]	IOANNOU I , VASSILIOU V , CHRISTOPHOROU C ,et al. Distributed artificial intelligence solution for D2D communication in 5G networks[J]. IEEE Systems Journal, 2020,14(3): 4232-4241.
[85]	XU J , GU X Y , FAN Z Q . D2D power control based on hierarchical extreme learning machine[C]// Proceedings of 2018 IEEE 29th Annual International Symposium on Personal,Indoor and Mobile Radio Communications (PIMRC). Piscataway: IEEE Press, 2018: 1-7.
[86]	HAMDI M , YUAN D , ZAIED M . GA-based scheme for fair joint channel allocation and power control for underlaying D2D multicast communications[C]// Proceedings of 2017 13th International Wireless Communications and Mobile Computing Conference (IWCMC). Piscataway: IEEE Press, 2017: 446-451.
[87]	LIU Y , YUAN X L , XIONG Z H ,et al. Federated learning for 6G communications: Challenges,methods,and future directions[J]. China Communications, 2020,17(9): 105-118.
[88]	DANG S P , AMIN O , SHIHADA B ,et al. What should 6G be?[J]. Nature Electronics, 2020,3(1): 20-29.

人工智能算法	优化目标	卸载方式	参考文献
MADDPG	时延、信道利用率、信道成功接入率	全卸载	参考文献[14]
DNN	兼顾时延与能耗	全卸载	参考文献[15]
深度强化学习	兼顾时延与能耗	部分卸载	参考文献[18]
DNN、SNN	时延、任务错误率	部分卸载	参考文献[16-17]
improved DNN	计算速率	全卸载	参考文献[20]
DDPG	兼顾时延与能耗	全卸载	参考文献[19]
CNN	时延	部分卸载	参考文献[21]
DQN	兼顾时延与能耗	全卸载	参考文献[22]
AHP-DQN	兼顾时延与能耗	全卸载	参考文献[23]

网络	4	8	16	32	64
CsiNet^[67]	2 103 904	1 055 072	530 656	268 448	137 344
CsiNet+^[68]	2 122 340	1 073 508	549 092	286 884	—
LSTM-CsiNet^[69]	10 247 148	—	7 484 688	7 024 272	6 794 064
LSTM-Attention^[70]	2 924 912	—	582 704	281 936	141 152
AnciNet^[75]	2 289 334	—	716 086	453 878	322 774

压缩率	CNR（dB）	CsiNet^[67]	AnciNet^[75]
16	0	-2.76	-8.70
	5	-6.24	-11.64
	10	-8.71	-13.31
	15	-9.56	-14.42
	20	-10.03	-14.84
	25	-10.19	-14.99
32	0	-1.94	-7.47
	5	-4.94	-9.26
	10	-7.23	-9.88
	15	-7.83	-10.42
	20	-8.09	-10.55
	25	-8.17	-10.60
64	0	-0.75	-6.49
	5	-3.45	-7.65
	10	-4.80	-7.92
	15	-5.28	-8.30
	20	-5.45	-8.37
	25	-5.52	-8.40

人工智能在5G系统中的应用综述

An survey on application of artificial intelligence in 5G system

在线阅读

PDF下载

可视化

摘要/Abstract

引用本文

使用本文

图/表 10

参考文献 88

相关文章 15

Metrics

推荐阅读 0

[1]	郭泽华, 朱昊文, 徐同文. 面向分布式机器学习的网络模态创新[J]. 电信科学, 2023, 39(6): 44-51.
[2]	王妍, 彭莹. 国际电信联盟（ITU）6G标准化研究[J]. 电信科学, 2023, 39(6): 129-138.
[3]	张辰, 王红凯, 毛冬, 潘司晨, 赵帅. 面向电力终端的轻量化5G硬加密通信模组研究及应用[J]. 电信科学, 2023, 39(6): 159-169.
[4]	胡珈玮, 刘晓谦, 唐昕柯, 董宇涵. 基于DQN的UUV辅助水下无线光通信轨迹规划系统[J]. 电信科学, 2023, 39(5): 42-47.
[5]	马晓亮, 刘英, 杜德泉, 安玲玲. 运营商智能客服的关键技术和发展趋势[J]. 电信科学, 2023, 39(5): 76-89.
[6]	许浩, 吴琳. 基于5G网络的VoWi-Fi互操作研究[J]. 电信科学, 2023, 39(5): 144-154.
[7]	王雪荣, 唐政治, 李银川, 齐美玉, 朱建波, 张亮. 基于优化决策树的时延敏感流智能感知调度[J]. 电信科学, 2023, 39(4): 120-132.
[8]	王建斌, 王淑春, 廖尚金, 施淑媛. 基于DCNN-LSTM负荷预测算法的5G基站节能系统研究[J]. 电信科学, 2023, 39(4): 133-141.
[9]	张乐, 马洪源. 运营商网络边缘云安全实践[J]. 电信科学, 2023, 39(4): 165-172.
[10]	刘思杨, 张云飞. 从智能网联1.0到智能网联2.0：面向双智的实时数字孪生城市构建[J]. 电信科学, 2023, 39(3): 32-44.
[11]	廖熙雯, 冷甦鹏, 明昱君, 李天扬. 基于数字孪生的城市交通流智能预测与导引策略[J]. 电信科学, 2023, 39(3): 70-79.
[12]	刘光海, 肖天, 李贝, 程新洲, 薛永备, 李一, 朱小萌, 郑雨婷. 4G载波向5G重耕之前的5G业务覆盖能力研究[J]. 电信科学, 2023, 39(3): 115-123.
[13]	蒋瑞红, 冯一哲, 孙耀华, 郑海娜. 面向低轨卫星网络的组网关键技术综述[J]. 电信科学, 2023, 39(2): 37-47.
[14]	王淑玲, 孙杰, 王鹏, 杨爱东. 云边协同中的资源调度优化[J]. 电信科学, 2023, 39(2): 163-170.
[15]	康宇, 刘雅琼, 赵彤雨, 寿国础. AI算法在车联网通信与计算中的应用综述[J]. 电信科学, 2023, 39(1): 1-19.