基于5G无人机通信的多智能体异构网络选择方法

doi:10.11959/j.issn.1000-0801.2022239

电信科学 ›› 2022, Vol. 38 ›› Issue (8): 28-36.doi: 10.11959/j.issn.1000-0801.2022239

• 专题：无人机空地无线通信技术 • 上一篇下一篇

基于5G无人机通信的多智能体异构网络选择方法

丁雨¹, 李晨凯¹, 韩会梅¹, 卢为党¹, 任元红², 高原³, 曹江³

¹ 浙江工业大学信息工程学院，浙江杭州 310023
² 北方自动控制技术研究所，山西太原 030006
³ 中国人民解放军军事科学院，北京 100091

修回日期:2022-08-11 出版日期:2022-08-20 发布日期:2022-08-01
作者简介:丁雨（1998- ），女，浙江工业大学信息工程学院硕士生，主要研究方向为无人机通信、智能通信
李晨凯（1996- ），男，浙江工业大学信息工程学院硕士生，主要研究方向为异构网络接入、智能通信
韩会梅（1990- ），女，浙江工业大学信息工程学院讲师，主要研究方向为无人机通信、大规模接入
卢为党（1984- ），男，浙江工业大学信息工程学院教授，主要研究方向为无人机通信、移动边缘计算
任元红（1984- ），男，北方自动控制技术研究所高级工程师，主要研究方向为指控系统设计
高原（1986- ），男，中国人民解放军军事科学院副研究员，主要研究方向为无人机通信
曹江（1960- ），男，中国人民解放军军事科学院研究员，主要研究方向为指挥信息系统理论
基金资助:
国家自然科学基金资助项目(61871348);国家自然科学基金资助项目(62222121)

Multi-agent heterogeneous network selection method based on 5G UAV communication

Yu DING¹, Chenkai LI¹, Huimei HAN¹, Weidang LU¹, Yuanhong REN², Yuan GAO³, Jiang CAO³

¹ College of Information Engineering, Zhejiang University of Technology, Hangzhou 310023, China
² North Automatic Control Technology Institute, Taiyuan 030006, China
³ Academy of Military Science of the PLA, Beijing 100091, China.

Revised:2022-08-11 Online:2022-08-20 Published:2022-08-01
Supported by:
The National Natural Science Foundation of China(61871348);The National Natural Science Foundation of China(62222121)

摘要/Abstract

摘要：

摘要：5G无人机通信网络和各种不同无线接入技术的结合使无线异构网络呈现多样化的发展趋势。然而，用户繁多且不同的业务请求对网络要求也不同，造成网络接入选择问题。提出了一种基于5G无人机通信的多智能体异构网络选择方法，将用户分为多个智能体，从用户端和网络端两个方面出发，将用户侧的时延和传输速率需求与网络侧的负载均衡需求综合考虑作为即时回报的相关参数，通过基于Nash Q-Learning的算法进行学习，得到异构网络环境下的网络选择决策模型。仿真结果表明，所提异构网络选择方法针对不同业务类型用户的需求均能选择合适的网络，同时均衡网络的负载，充分利用异构无线网络的资源。

关键词: 无人机通信, 异构网络选择, NashQ-Learning, 负载均衡

Abstract:

The combination of 5G UAV communication and different wireless access technologies makes wireless heterogeneous networks present a diversified development trend.However, various types of service requests by users have different requirements on the heterogeneous networks, which leads to the problem of network selection.A multi-agent heterogeneous network selection method based on 5G UAV communication was proposed.Specifically, the users were divided into multiple agents.From the two aspects of the user side and the network side, the delay and transmission rate requirements of the user side and the load balancing requirement of the network side were comprehensively considered as the relevant parameters of immediate reward.The simulation results show that the proposed heterogeneous network selection method can select the appropriate network according to the needs of users of different service types, balance the load of the network, and make full use of the resources of the heterogeneous wireless network.

Key words: UAV communication, heterogeneous network selection, Nash Q-Learning, load balancing

中图分类号:

TN925

丁雨, 李晨凯, 韩会梅, 卢为党, 任元红, 高原, 曹江. 基于5G无人机通信的多智能体异构网络选择方法[J]. 电信科学, 2022, 38(8): 28-36.

Yu DING, Chenkai LI, Huimei HAN, Weidang LU, Yuanhong REN, Yuan GAO, Jiang CAO. Multi-agent heterogeneous network selection method based on 5G UAV communication[J]. Telecommunications Science, 2022, 38(8): 28-36.

图/表 8

图1

表1

图2

图3

表2

图4

图5

图6

参考文献 19

[1]	贺子健, 艾元, 闫实 ,等. 无人机通信网络的容量与覆盖性能[J]. 电信科学, 2017,33(10): 65-70.
	HE Z J , AI Y , YAN S ,et al. Performance evaluation of capacity and coverage in UAV communication networks[J]. Telecommunications Science, 2017,33(10): 65-70.
[2]	LU W D , DING Y , GAO Y ,et al. Secure NOMA-based UAV-MEC network towards a flying eavesdropper[J]. IEEE Transactions on Communications, 2022,70(5): 3364-3376.
[3]	张祖凡, 张宇 . 基于3D-Markov链的异构网络用户QoE分析方法[J]. 中国科学:信息科学, 2016,46(1): 85-99.
	ZHANG Z F , ZHANG Y . QoE analysis method for heterogeneous network user based on 3D-Markov chain[J]. Scientia Sinica(Informationis), 2016,46(1): 85-99.
[4]	刘军, 李晓楠 . 基于层次分析法的 WLAN/蜂窝网络切换判决算法[J]. 通信学报, 2013,34(2): 65-72.
	LIU J , LI X N . Handover algorithm for WLAN/cellular networks with analytic hierarchy process[J]. Journal on Communications, 2013,34(2): 65-72.
[5]	盛洁, 马冬 . 异构无线网络业务接入多目标优化控制算法[J]. 电子学报, 2016,44(2): 282-288.
	SHENG J , MA D . Multi-objective optimal based service access control algorithm for heterogeneous wireless networks[J]. Acta Electronica Sinica, 2016,44(2): 282-288.
[6]	ZHOU W A , XU Y J , LIANG T ,et al. Optimal power allocation for heterogeneous network capacity maximization[J]. China Communications, 2013,10(9): 97-103.
[7]	CHANG B J , CHEN J F . Cross-layer-based adaptive vertical handoff with predictive RSS in heterogeneous wireless networks[J]. IEEE Transactions on Vehicular Technology, 2008,57(6): 3679-3692.
[8]	石文孝, 范绍帅, 王柟 ,等. 基于模糊神经网络的异构无线网络接入选择算法[J]. 通信学报, 2010,31(9): 151-156.
	SHI W X , FAN S S , WANG N ,et al. Fuzzy neural network based access selection algorithm in heterogeneous wireless networks[J]. Journal on Communications, 2010,31(9): 151-156.
[9]	MIAO J , HU Z , YANG K ,et al. Joint power and bandwidth allocation algorithm with QoS support in heterogeneous wireless networks[J]. IEEE Communications Letters, 2012,16(4): 479-481.
[10]	CHEN H N , WU H Y , KUMAR S ,et al. Minimum-cost data delivery in heterogeneous wireless networks[J]. IEEE Transactions on Vehicular Technology, 2007,56(6): 3511-3523.
[11]	LIU S M , PAN S , MI Z K ,et al. A simple additive weighting vertical handoff algorithm based on SINR and AHP for heterogeneous wireless networks[J]. 2010 International Conference on Intelligent Computation Technology and Automation, 2010,1: 347-350.
[12]	魏淑芝, 朱琦 . 基于网络选择的视频通信带宽博弈算法[J]. 通信学报, 2015,36(2): 216-224.
	WEI S Z , ZHU Q . Bandwidth allocation games based on network selection for video communication[J]. Journal on Communications, 2015,36(2): 216-224.
[13]	CHAMODRAKAS I , MARTAKOS D . A utility-based fuzzy TOPSIS method for energy efficient network selection in heterogeneous wireless networks[J]. Applied Soft Computing, 2011,11(4): 3734-3743.
[14]	GOYAL R K , KAUSHAL S , SANGAIAH A K . The utility based non-linear fuzzy AHP optimization model for network selection in heterogeneous wireless networks[J]. Applied Soft Computing, 2018,67: 800-811.
[15]	赵彦清, 朱琦 . 基于 Q 学习的异构网络选择新算法[J]. 计算机应用, 2011,31(6): 1461-1464,1479.
	ZHAO Y Q , ZHU Q . New Q-learning based heterogeneous network selection algorithm[J]. Journal of Computer Applications, 2011,31(6): 1461-1464,1479.
[16]	XIE J L , GAO W J , LI C R . Heterogeneous network selection optimization algorithm based on a Markov decision model[J]. China Communications, 2020,17(2): 40-53.
[17]	CHEN J L , YIN M X , DUAN X H ,et al. Q-learning based selection strategies for load balance and energy balance in heterogeneous networks[C]// Proceedings of 2020 5th International Conference on Computer and Communication Systems (ICCCS). Piscataway:IEEE Press, 2020: 728-732.
[18]	WANG X Q , SU X , LIU B . A novel network selection approach in 5G heterogeneous networks using Q-learning[C]// Proceedings of 2019 26th International Conference on Telecommunications (ICT). Piscataway:IEEE Press, 2019: 309-313.
[19]	YANG J , FENG L , JIN T . Enabling sector scheduling for 5G-CPE dense networks[J]. Security and Communication Networks, 2020(7): 1-18.

负载占用率	量化等级
[0,0.5)	1
[0.5,0.75)	2
[0.75,0.875)	3
[0.875,1]	4

网络	时延/ms	传输速率/(Gbit·s^-1)
5G CPE	20～45	1.2～1.4
5G 无人机	10～30	1.4～1.6
Wi-Fi	40～70	1.7～1.9

基于5G无人机通信的多智能体异构网络选择方法

Multi-agent heterogeneous network selection method based on 5G UAV communication

在线阅读

PDF下载

可视化

摘要/Abstract

引用本文

使用本文

图/表 8

参考文献 19

相关文章 15

Metrics

推荐阅读 0

[1]	刘晨熙, 马睿, 彭木根. 无人机通信感知一体化：架构、技术与展望[J]. 电信科学, 2023, 39(2): 1-9.
[2]	王兆辉, 沈剑良, 张霞, 陈艇. FALB：一种FC协议链路聚合算法[J]. 电信科学, 2021, 37(9): 105-111.
[3]	淡振雷,吴雪雯,欧阳键,汪萧萧,顾晨伟,林敏. 基于门限判断DF协议的多无人机中继传输中断性能分析[J]. 电信科学, 2020, 36(8): 103-111.
[4]	罗斯宁,王化龙,李弘宇,彭蔚. 基于改进蚁群算法的云计算用户任务调度算法[J]. 电信科学, 2020, 36(2): 95-100.
[5]	乐光学,戴亚盛,杨晓慧,朱友康,游真旭,刘建生. 边缘计算多约束可信协同任务迁移策略[J]. 电信科学, 2019, 35(11): 36-50.
[6]	王文博,叶庆卫,周宇,陆志华. 基于排队论综合指标评估的动态负载均衡算法[J]. 电信科学, 2018, 34(7): 86-91.
[7]	刘海鹏. 基于负载均衡的MEH静态切换机制[J]. 电信科学, 2018, 34(7): 118-127.
[8]	孙乔,邓卜侨,王志强,裴旭斌. 一种基于分布式服务器集群的可扩展负载均衡策略技术[J]. 电信科学, 2017, 33(9): 190-196.
[9]	包晓安,魏雪,陈磊,胡国亨,张娜. 基于mean-variance的服务集群负载均衡方法[J]. 电信科学, 2017, 33(1): 1-8.
[10]	李鑫滨,高梦玲,闫磊. 一种负载均衡且能量高效的水下传感网络分簇协议[J]. 电信科学, 2016, 32(11): 42-49.
[11]	程日涛,徐德平,张炎炎. LTE FDD网络规划原则及部署策略[J]. 电信科学, 2015, 31(Z1): 11-16.
[12]	鲍楠,夏玮玮,鲍煦. 异构网络融合环境下基于加权二分图的网络选择算法[J]. 电信科学, 2015, 31(9): 44-50.
[13]	刘凯,赵建业,刘志敏. 基于指派模型的LTE-A异构网节能负载均衡算法[J]. 电信科学, 2015, 31(2): 22-28.
[14]	赵振东,牛伟娇,韩东升,丁莎莎. 异构无线网络中边缘用户小区选择算法[J]. 电信科学, 2015, 31(12): 52-57.
[15]	刘悦,郭晓磊,张迅. 基于功率控制和信道分配的网络优化算法[J]. 电信科学, 2015, 31(10): 93-98.