面向B5G/6G的三三三网络体系架构和优化学习机制

doi:10.11959/j.issn.1000-436x.2021095

通信学报 ›› 2021, Vol. 42 ›› Issue (4): 62-75.doi: 10.11959/j.issn.1000-436x.2021095

所属专题： 6G

• 专题：面向未来移动网络的大规模组网关键技术 • 上一篇下一篇

面向B5G/6G的三三三网络体系架构和优化学习机制

朱近康¹^,², 柴名扬¹^,², 周武旸¹^,²

¹ 中国科学技术大学信息科学技术学院，安徽合肥 230027
² 中国科学院无线光通信重点实验室，安徽合肥 230027

修回日期:2021-03-15 出版日期:2021-04-25 发布日期:2021-04-01
作者简介:朱近康（1943- ），男，四川内江人，中国科学技术大学教授、博士生导师，主要研究方向为无线通信理论、技术和网络的研究、无线大数据和无线 AI、绿色无线、5G/6G的创新技术。
柴名扬（1996- ），男，河南开封人，中国科学技术大学硕士生，主要研究方向为无线大数据、无线AI和混合预编码。
周武旸（1972- ），男，安徽合肥人，博士，中国科学技术大学教授、博士生导师，主要研究方向为移动通信与无线通信网、卫星移动通信等。
基金资助:
国家重点研发计划基金资助项目(2018YFB1801105);国家自然科学基金资助项目(61631018)

Three-three-three network architecture and learning optimization mechanism for B5G/6G

Jinkang ZHU¹^,², Mingyang CHAI¹^,², Wuyang ZHOU¹^,²

¹ College of Information Science and Technology, University of Science and Technology of China, Hefei 230027, China
² Key Laboratory of Wireless Optical Communications, Chinese Academy of Sciences, Hefei 230027, China

Revised:2021-03-15 Online:2021-04-25 Published:2021-04-01
Supported by:
The National Key Research and Development Program of China(2018YFB1801105);The National Natural Science Foundation of China(61631018)

摘要/Abstract

摘要：

面对未来B5G/6G网络是大连接复杂智能网络，极其大量的用户连接、需求连接、服务连接，加之3G、4G、5G 甚至 6G 的综合运用，将导致网络变得极其复杂的挑战，提出了一种三三三网络体系架构，它是一个包含3类网络（核心网、接入网、终端网）、3种资源（频率带宽、功耗、时延）和3项需求（生活、工作、服务）的三维立体综合优化的体系架构，简称三三三网络。进而，论证了三维立体复杂体系的数学计算式，给出了知识+数据驱动学习模型和利用知识学习机制进行智能处理的优化方法。最后，给出了三三三网络的数值例和可达性能。研究结果表明，所提三三三网络体系架构和优化方法对于设计和运行未来的大连接复杂智能网络是有益的。

关键词: 三三三网络体系架构, 知识学习机制, 知识+数据驱动学习模型, 复杂网络实时动态优化, 大连接复杂智能网络

Abstract:

Aiming at the problem that the future B5G/6G network is a complex intelligent network with large connections, coupled with the comprehensive application of 3G, 4G, 5G and even 6G, the future networks will inevitably become extremely complex, a three-three-three network architecture was proposed that was a network that includes three types of networks (core network, access network and terminal network), three resources (frequency band, power and time consumptions) and three requirements (active, work and service), which was a three-dimensional comprehensive optimization system architecture, referred to as the three-three-three network.Furthermore, the mathematical basic formulas of the three-dimensional complex network were analyzed, the knowledge + data-driven learning model and the optimization method of intelligent processing using the knowledge learning mechanism were presented.Finally, the numerical example and reachable performance of the three-three-three network were given.Those results demonstrate that the proposed network architecture and the learning optimization mechanism are beneficial for designing future large-connected complex intelligent networks.

Key words: three-three-three network architecture, knowledge learning mechanism, knowledge + data driving learning model, real-time dynamic optimization of complex network, large connections to complex intelligent network

中图分类号:

TN915.5

朱近康, 柴名扬, 周武旸. 面向B5G/6G的三三三网络体系架构和优化学习机制[J]. 通信学报, 2021, 42(4): 62-75.

Jinkang ZHU, Mingyang CHAI, Wuyang ZHOU. Three-three-three network architecture and learning optimization mechanism for B5G/6G[J]. Journal on Communications, 2021, 42(4): 62-75.

图/表 12

图1

图2

图3

图4

图5

图6

图7

表1

表2

通过学习机制获得的频率带宽开销"

网络连接	n	γ	β	B/MHz	C/(Mbit.s^-1)
Net_3,3	100 000	1	1	1	100 000
Net_3,2	20000	1	2	7.5	300 000
Net_3,1	1000	1	2	25	50 000
Net_2,3	800	1	2	11.5	18 400
Net_2,2	16	6	4	147.2	1 8841.6
Net_2,1	1	12	6	391	9384
合计	—	—	—	$583 . 2$	$496626$

表2

图8

图9

图10

参考文献 16

[1]	WANG X F , CHEN G R . Complex networks:small-world,scale-free and beyond[J]. IEEE Circuits and Systems Magazine, 2003,3(1): 6-20.
[2]	ALBERT R , BARABáSI A L . Statistical mechanics of complex networks[J]. Reviews of Modern Physics, 2002,74(1): 47.
[3]	NEWMAN M E J . The structure and function of complex networks[J]. SIAM Review, 2003,45(2): 167-256.
[4]	WANDELT S , SHI X , SUN X Q . Complex network metrics:can deep learning keep up with tailor-made reference algorithms?[J]. IEEE Access, 2020,8: 68114-68123.
[5]	LAMBIOTTE R , DELVENNE J C , BARAHONA M . Random walks,Markov processes and the multiscale modular organization of complex networks[J]. IEEE Transactions on Network Science and Engineering, 2014,1(2): 76-90.
[6]	GLISIC S , LORENZO B , KOVACEVIC I ,et al. Modeling dynamics of complex wireless networks[C]// 2013 International Conference on High Performance Computing ＆ Simulation. Piscataway:IEEE Press, 2013: 694-704.
[7]	LAMBIOTTE R , . Multi-scale modularity in complex networks[C]// 8th International Symposium on Modeling and Optimization in Mobile,Ad Hoc,and Wireless Networks. Piscataway:IEEE Press, 2010: 546-553.
[8]	LU R Q , YU W W , LYU J ,et al. Synchronization on complex networks of networks[J]. IEEE Transactions on Neural Networks and Learning Systems, 2014,25(11): 2110-2118.
[9]	ZHANG Q J , LU J N , LU J H ,et al. Adaptive feedback synchronization of a general complex dynamical network with delayed nodes[J]. IEEE Transactions on Circuits and Systems II:Express Briefs, 2008,55(2): 183-187.
[10]	SERGIOU C , LESTAS M , ANTONIOU P ,et al. Complex systems:a communication networks perspective towards 6G[J]. IEEE Access, 2020,8: 89007-89030.
[11]	ZHU J K , ZHAO M , ZHANG S H ,et al. Exploring the road to 6G:ABC—foundation for intelligent mobile networks[J]. China Communications, 2020,17(6): 51-67.
[12]	SHANNON C E . A mathematical theory of communication[J]. Bell System Technical Journal, 1948,27(4): 623-656.
[13]	ZHU J K , LI X . Capacity-power consumption and energy-efficiency evaluation of green wireless networks[J]. China Communications, 2012,9(2): 13-21.
[14]	MAHMUD A , HAMDI K A . A unified framework for the analysis of fractional frequency reuse techniques[J]. IEEE Transactions on Communications, 2014,62(10): 3692-3705.
[15]	ZHU J K , ZHAO M , ZHOU S L . An optimization design of ultra dense networks balancing mobility and densification[J]. IEEE Access, 2018,6: 32339-32348.
[16]	ZHU J K , GONG C , ZHANG S H ,et al. Foundation study on wireless big data:concept,mining,learning and practices[J]. China Communications, 2018,15(12): 1-15.

网络	连接距离/m	用户数/个	速度区间/（km·s^-1）		流量/（Mbit·s^-1）	附加比例	总量（Mbit·s^-1）
全网	[0,5000)	100 000	—	—	450000	1%	454500
Net_3,3	[0,1)	60 000	[0,1)	40000	4000	1%	4040
Net_3,2	[1,5)	30 000	[1,5)	30000	150000	1%	151500
Net_3,1	[5,10)	20 000	[5,10)	10000	250000	1%	252500
Net_2,3	[10,20)	5000	[10,20)	5000	11500	1%	11615
Net_2,2	[20,250)	10000	[20,250)	10000	23000	1%	23230
Net_2,1	[250,5000)	5000	[250,300)	5000	11500	1%	11615

面向B5G/6G的三三三网络体系架构和优化学习机制

Three-three-three network architecture and learning optimization mechanism for B5G/6G

在线阅读

PDF下载

可视化

摘要/Abstract

引用本文

使用本文

图/表 12

参考文献 16

相关文章 0

Metrics

推荐阅读 0