基于MHA-MAD的近海光无线融合接入网络部署算法

李学华; 郗童; 王鑫; 黄翔

doi:10.13756/j.gtxyj.2025.250076

您当前的位置：

首页 >

文章列表页 >

基于MHA-MAD的近海光无线融合接入网络部署算法

专题：海洋通信与传感网络 | 更新时间：2025-08-16

- 基于MHA-MAD的近海光无线融合接入网络部署算法
- Offshore Optical-wireless Integrated Access Network Deployment Algorithm based on MHA-MAD
- 光通信研究 2025年第4期
- 作者机构：
  
  1.北京信息科技大学　智能通信与计算研究所，北京　102206
  2.国防科技大学　信息系统工程全国重点实验室，长沙　410073
- 作者简介：
  
  李学华（1977-），女，湖北荆州人。教授，博士，主要研究方向为无线通信关键技术、物联网技术和智能边缘技术等。
  王鑫，副教授。E-mail：xinwang@bistu.edu.cn
- 基金信息：
  
  北京市自然科学基金—海淀原始创新联合基金资助项目(L222004);北京市教委科技计划一般资助项目(KM202311232012);江苏省自然科学基金资助项目(BK20232028)
- DOI：10.13756/j.gtxyj.2025.250076
  中图分类号： TN929
- 收稿日期：2025-03-05，
  
  修回日期：2025-05-21，
  
  纸质出版日期：2025-08-10
- 稿件说明：
移动端阅览
李学华，郗童，王鑫，等. 基于MHA-MAD的近海光无线融合接入网络部署算法[J]. 光通信研究，2025(4): 250076.

Li X H, Xi T, Wang X, et al. Offshore Optical-wireless Integrated Access Network Deployment Algorithm based on MHA-MAD[J]. Study on Optical Communications, 2025(4): 250076.
李学华，郗童，王鑫，等. 基于MHA-MAD的近海光无线融合接入网络部署算法[J]. 光通信研究，2025(4): 250076. DOI： 10.13756/j.gtxyj.2025.250076.

Li X H, Xi T, Wang X, et al. Offshore Optical-wireless Integrated Access Network Deployment Algorithm based on MHA-MAD[J]. Study on Optical Communications, 2025(4): 250076. DOI： 10.13756/j.gtxyj.2025.250076.

摘要

【目的】

随着近海区域业务量的快速增长，带宽需求呈现出指数级增长趋势，承载业务的第五代移动通信技术（5G）及后5G（B5G）下一代无线接入网络（NG-RAN）资源即将枯竭，波分复用无源光网络（WDM-PON）因其高带宽等优势，成为支持5G/B5G NG-RAN的有效承载方案。然而，近海复杂多变的环境为WDM-PON的网络部署带来了严峻挑战，如高昂的部署成本、大规模的路径损耗以及恶劣的水下环境等，亟需通过优化网络部署策略降低成本、风险和传输损耗等，以构建适应近海环境的网络。

【方法】

文章提出了一种多头注意力增强的多智能体深度Q网络（MHA-MAD）算法，通过多头注意力机制高效提取网络环境的关键特征，并为不同特征赋予动态权重，从而提升建模精度。同时，采用多智能体框架，使多个智能体在共享网络环境中协作与同步决策，实现网络部署的全局优化。

【结果】

与现有基准方法相比，MHA-MAD算法在网络部署中使性能提高了近42%，其结果接近理论最优解。此外，与未利用多头注意力机制的多智能体深度Q网络（DQN）算法相比，MHA-MAD算法在最小化网络部署总成本、节点功耗、链路衰减和网络风险的联合优化目标上，性能提高了近8%。

【结论】

MHA-MAD算法为面向近海场景5G/B5G NG-RAN的WDM-PON部署与优化提供了新思路。

Abstract

【Objective】

With the rapid growth of business volume in the nearshore area

the demand for bandwidth is showing an exponential growth trend. The resources of the 5th Generation Mobile Communication Technology (5G) and Beyond-5G (B5G) Next Generation Radio Access Network (NG-RAN) that carry the business are about to be exhausted. Wavelength Division Multiplexing-Passive Optical Network (WDM-PON)

with its advantages such as high bandwidth

has become an effective solution to support 5G/B5G NG-RAN. However

the complex and variable offshore environment poses severe challenges for the deployment of WDM-PON networks. These challenges include high deployment costs

substantial path losses

and harsh underwater conditions. There is an urgent need to optimize network deployment strategies to reduce costs

risks

and transmission losses in order to build a network that is suitable for the offshore environment.

【Methods】

This study proposes a Multi-Head Attention enhanced Multi-Agent Deep Q-Network (MHA-MAD) algorithm. It efficiently extracts key features of the network environment using multi-head attention mechanism and assigns dynamic weights to different features

thereby improving modeling accuracy. Simultaneously

the multi-agent structure allows multiple agents to collaborate and make synchronized decisions within a shared network environment

promoting global optimization in network deployment.

【Results】

Compared to other benchmarks

the MHA-MAD algorithm improves performance in network deployment by nearly 42%

with results approaching the theoretical optimum. Furthermore

compared to multi-agent Deep Q-Network (DQN) method without the multi-head attention

MHA-MAD algorithm improves the performance by nearly 8% in the joint optimization objective of minimizing overall network deployment costs

node power consumption

link attenuation

and network deployment risk probabilities.

【Conclusion】

MHA-MAD provides new insights for the deployment and optimization of WDM-PON to support 5G/B5G NG-RAN in offshore scenarios.

关键词

Keywords

references

Zhu S , Chen X , Liu X , et al . Recent Progress in and Perspectives of Underwater Wireless Optical Communication [J ] . Progress in Quantum Electronics , 2020 , 73 : 100274 .

Shayea I , Ergen M , Hadri Azmi M , et al . Key Challenges, Drivers and Solutions for Mobility Management in 5G Networks: A Survey [J ] . IEEE Access , 2020 , 8 : 172534 - 172552 .

吴佳丽 , 刘向南 , 孙春蕾 , 等 . 海洋移动通信网络无线资源管控 [J ] . 移动通信 , 2024 , 48 ( 11 ): 77 - 85 .

Wu J L , Liu X N , Sun C L , et al . Wireless Resource Management for Marine Mobile Communication Networks [J ] . Mobile Communications , 2024 . 48 ( 11 ): 77 - 85 .

Satyanarayana K , Abhinov B . Recent Trends in Future Proof Fiber Access Passive Networks: GPON and WDM PON [C ] // International Conference on Recent Trends in Information Technology 2014 . Chennai, India : IEEE , 2014 : 1 - 5 .

Xu Z , Zhuang L , Zhuang W , et al . Meta Relational Learning-based Service-Tailored VNF Deployment for B5G Network Slice [J ] . IEEE Internet of Things Journal , 2023 , 10 ( 24 ): 22542 - 22554 .

Xu C , Song S , Liu J , et al . An Efficient Deployment Scheme with Network Performance Modeling for Underwater Wireless Sensor Networks [J ] . IEEE Internet of Things Journal , 2024 , 11 ( 5 ): 8345 - 8359 .

Bushnaq M , Zhilin I V , Masi G D , et al . Automatic Network Slicing for Admission Control, Routing, and Resource Allocation in Underwater Acoustic Communication Systems [J ] . IEEE Access , 2022 , 10 : 134440 - 134454 .

Li J , Yang T , Feng H . Intelligent Maritime Communications Enabled by Deep Reinforcement Learning [C ] // IEEE/CIC International Conference on Communications in China (ICCC) 2019 . Changchun, China : IEEE , 2019 : 786 - 791 .

Salman Hassan S , Park S B , Huh E N , et al . Seamless and Intelligent Resource Allocation in 6G Maritime Networks Framework via Deep Reinforcement Learning [C ] // International Conference on Information Networking (ICOIN) 2023 . Bangkok, Thailand : IEEE , 2023 : 505 - 510 .

Yi J , Qiao G , Yuan F , et al . Sensor Deployment Strategies for Target Coverage Problems in Underwater Acoustic Sensor Networks [J ] . IEEE Communications Letters , 2023 , 27 ( 3 ): 836 - 840 .

Zhao Z , Gao G , Gan W , et al . Multi-objective Optimization for Submarine Optical Cable Route Planning based on Cross Reinforcement Learning [J ] . Journal of Optical Communications and Networking , 2024 , 16 ( 10 ): 1018 - 1033 .

周烨琦 , 王锐 . 海底沙波对光缆铺设放缆余量计算的影响 [J ] . 海洋工程装备与技术 , 2023 , 10 ( 04 ): 135 - 139 .

Zhou Y Q , Wang R . Influence of Submarine Bedforms on the Determination of Length Redundancy for Optical Communication Cable Laying [J ] . Ocean Engineering Equipment and Technology , 2023 , 10 ( 04 ): 135 - 139 .

陈宇俊 , 解江 , 张泽 , 等 . 海底光缆环境影响因素综述 [J ] . 电子产品可靠性与环境试验 , 2018 , 36 ( S1 ): 232 - 236 .

Chen Y J , Xie J , Zhang Z , et al . Review on Environmental Influence Factors of Submarine Optical Fiber Cable [J ] . Electronic Product Reliability and Environmental Testing , 2018 , 36 ( S1 ): 232 - 236 .

Zhang J , Wang H . Development of Offshore Wind Power and Foundation Technology for Offshore Wind Turbines in China [J ] . Ocean Engineering , 2022 , 266 : 113256 .

Wang X , Ji Y , Zhang J , et al . Joint Optimization of Latency and Deployment Cost over TDM-PON based MEC-enabled Cloud Radio Access Networks [J ] . IEEE Access , 2020 , 8 : 681 - 696 .

浏览量

下载量

CSCD

CNKI被引量

文章被引用时，请邮件提醒。

提交

工具集

关联资源

暂无数据