| 119 | 0 | 476 |
| 下载次数 | 被引频次 | 阅读次数 |
针对煤矿井下复杂环境中第五代移动通信技术（5th-Generation Mobile Communication Technology,5G）网络覆盖性能优化的问题，提出一种基于深度强化学习的矿井5G优化方案。面向10km主运巷道场景，综合考虑巷道截面尺寸、壁面粗糙度、设备遮挡等多重传输损耗因素，建立融合视距/非视距路径损耗模型与粗糙度衰减因子的信号传播数学模型。将深度Q网络作为价值函数近似器的强化学习智能体，并通过基站部署与发射功率将在线优化转化为多目标决策问题，以最小基站数量实现覆盖率最大化。采用动态功率调整机制，以实时优化基站发射功率，从而适应局部信号衰减的突发变化。实验结果表明，该方案可以实现95%以上的覆盖率，相较于传统静态方案减少了28%基站部署，显著提升了井下5G网络覆盖性能，并能够降低部署成本与运行功耗。
Abstract：Aiming at the optimization of 5 Gnetwork coverage performance in the complex environment of coal mine underground,a 5 Goptimization scheme based on deep reinforcement learning is proposed.For the 10 km main transport roadway scenario,multiple transmission loss factors such as roadway cross-section size,wall roughness,and equipment occlusion are comprehensively considered,and a signal propagation mathematical model integrating the line-of-sight/nonline-of-sight path loss model and the roughness attenuation factor is established.A deep Q-network is adopted as the value-function approximator for the learning agent,transforming the joint online optimization of base-station placement and transmit power into a multi-objective decision problem that maximizes the coverage while minimizing the number of base stations.Adopt a dynamic power-adjustment mechanism,enabling real-time adaptation to abrupt local signal degradations.Experimental results confirm that the scheme achieves a coverage exceeding 95%,while reducing the number of deployed base stations by 28% compared with a conventional static layout,thereby markedly enhancing the underground 5 Gcoverage and lowering the deployment costs and operational power consumption.
[1]孙继平．煤矿智能化与矿用5G[J]．工矿自动化，2020,46(8):1-7.SUN J P.Coal mine intelligence and mine-used 5G[J].Industry and Mine Automation,2020,46(8):1-7.(in Chinese)
[2]王国法．煤矿智能化最新技术进展与问题探讨[J]．煤炭科学技术，2022,50(1):1-27.WANG G F.New technological progress of coal mine intelligence and its problems[J].Coal Science and Technology,2022,50(1):1-27.(in Chinese)
[3]何勇，徐元涛．5G通信技术在智能化煤矿的应用与研究[J]．能源与节能，2023(3):167-169.HE Y,XU Y T.Application and research of 5Gcommunication technology in intelligent coal mines[J].Energy and Energy Conservation,2023(3):167-169.(in Chinese)
[4] LEINONEN M E,HOVINEN V,VUOHTONIEMI R,et al.Radio channel characterization measurements in an underground mine for 5Gat sub-6GHz and millimeter wave frequencies[J].International Journal of Microwave and Wireless Technologies,2025,17(5):850-861.
[5]李啸威．人工智能在5G无线网络优化中的设计与实现[J]．数字技术与应用，2024,42(9):60-62.LI X W.Design and implementation of artificial intelligence in optimization of 5Gwireless network[J].Digital Technology&Application,2024,42(9):60-62.(in Chinese)
[6]尹东升．5G-700 MHz技术在三元矿井下应用[J]．现代矿业，2023,39(7):252-255.YIN D S.Application of 5G-700 MHz technology in Sanyuan Mine[J].Modern Mining,2023,39(7):252-255.(in Chinese)
[7]孙继平，彭铭，刘斌．矿井无线传输测试分析与矿用5G优选工作频段研究[J]．工矿自动化，2024,50(10):1-11.SUN J P,PENG M,LIU B.Analysis of wireless transmission tests in mines and preferred working frequency bands for mining 5G[J].Journal of Mine Automation,2024,50(10):1-11.(in Chinese)
[8]孙继平，彭铭．矿井无线电波防爆安全发射功率研究[J]．工矿自动化，2024,50(3):1-5.SUN J P,PENG M.Research on the safe transmission power of mine radio wave explosion prevention[J].Journal of Mine Automation,2024,50(3):1-5.(in Chinese)
[9]索智文，王亚坤．煤矿井下重点场所5G覆盖性能研究及验证[J]．工矿自动化，2025,51(2):34-40.SUO Z W,WANG Y K.Research and verification of5Gcoverage performance in key areas of underground coal mines[J].Journal of Mine Automation,2025,51(2):34-40.(in Chinese)
[10]张锟，赵伟．基于人工智能的5G无线网规划和优化分析[J]．中国宽带，2024(10):61-63.ZHANG K,ZHAO W.Planning and optimization analysis of 5G wireless network based on artificial intelligence[J].China Broad Band,2024(10):61-63.(in Chinese)
[11]胡贵宾，赵川斌．基于机器学习和波束配置的5G天线方位角智能优化算法及实践[J]．广东通信技术，2024,44(4):37-40.HU G B,ZHAO C B.Intelligent azimuth optimization algorithm and practice of 5Gantenna based on machine learning and beam configuration[J].Guangdong Communication Technology,2024,44(4):37-40.(in Chinese)
[12]冯卫国．5G技术在煤矿智能化中的应用[J]．能源与节能，2025(2):238-240.FENG W G.Application of 5Gtechnology in coal mine intelligence[J].Energy and Energy Conservation,2025(2):238-240.(in Chinese)
[13]YAN M,FENG G,ZHOU J H,et al.Intelligent resource scheduling for 5Gradio access network slicing[J].IEEE Transactions on Vehicular Technology,2019,68(8):7691-7703.
[14]AL-TAHMEESSCHI A,TALVITIE J,LóPEZBENíTEZ M,et al.Multi-objective deep reinforcement learning for 5Gbase station placement to support localisation for future sustainable traffic[C]//2024Joint European Conference on Networks and Communications&6GSummit.Antwerp:IEEE,2024:493-498.
[15]SORANZO E,GUARDIANI C,WU W.Reinforcement learning for the face support pressure of tunnel boring machines[J].Geosciences,2023,13(3):82.
[16]樊昌信，曹丽娜．通信原理[M].7版．北京：国防工业出版社，2015.FAN C X,CAO L N.Principles of communications[M].7th ed.Beijing:National Defense Industry Press,2015.(in Chinese)
[17]张侯，陈隆，陈汉章．基于无线网络通信的煤矿机电设备运行自动化监测系统设计[J]．电子设计工程，2025,33(17):154-157.ZHANG H,CHEN L,CHEN H Z.Design of an automated monitoring system for coal mine electromechanical equipment operation based on wireless network communication[J].Electronic Design Engineering,2025,33(17):154-157.(in Chinese)
[18] QIAN J Y,WU Y T,SALEEM A,et al.Path loss model for 3.5 GHz and 5.6 GHz bands in cascaded tunnel environments[J].Sensors,2022,22(12):4524.
[19]YOU Y S,JING L J,YANG Q H,et al.Analysis and modeling of radio propagation fading characteristics in tunnel construction[J].Heliyon,2024,10(4):e26231.
[20]LI B Y,DING T,WU Y H,et al.Modeling and optimization of wireless signal transmission characteristics of mine roadway based on 3Dray-tracing method[J].Applied Sciences,2024,14(4):1534.
[21]姚善化，吴先良，张量．矿井巷道壁粗糙度对电磁波传播损耗的影响[J]．合肥工业大学学报（自然科学版），2010,33(11):1725-1727.YAO S H,WU X L,ZHANG L.Influence of rough wall on electromagnetic waves propagation attenuation in mine tunnels[J].Journal of Hefei University of Technology(Natural Science),2010,33(11):1725-1727.(in Chinese)
[22]SHAHID S,ZAHRA H,QAISAR S B,et al.Radio link model for node deployment in underground mine sensor networks[J].Applied Sciences,2023,13(15):8987.
[23]3GPP.Study on channel model for frequencies from0.5to 100GHz:TR 38.901[S/OL].[2025-03-01].https：//www.3gpp.org/ftp/Specs/archive/38_series/38.901/38901-i00.zip.
[24]MNIH V,KAVUKCUOGLU K,SILVER D,et al.Human-level control through deep reinforcement learning[J].Nature,2015,518(7540):529-533.
[25]江雨霏，朱其新．深度强化学习下的管道气动软体机器人控制[J]．西安工程大学学报，2025,39(2):65-74.JIANG Y F,ZHU Q X.Pipe pneumatic soft robot control based on deep reinforcement learning[J].Journal of Xi’an Polytechnic University,2025,39(2):65-74.(in Chinese)
[26]MISMAR F B,EVANS B L,ALKHATEEB A.Deep reinforcement learning for 5G networks:Joint beamforming,power control,and interference coordination[J].IEEE Transactions on Communications,2020,68(3):1581-1592.
基本信息:
DOI：10.13682/j.issn.2095-6533.2025.06.002
中图分类号:TP18;TN929.5;TD655.3
引用信息:
[1]梁沫,王军选.基于深度强化学习的矿井5G优化方案[J].西安邮电大学学报,2025,30(06):11-20.DOI:10.13682/j.issn.2095-6533.2025.06.002.
基金信息:
国家自然科学基金项目（62071377）