Joint Cross-Medium Resource Allocation Algorithm for Dual-mode Communication Systems Based on Heterogeneous Multi-agent Reinforcement Learning

CHEN Zzhixiong; WEI Zihan

doi:10.11959/j.issn.1000-0801.DXKX260462

Chinese

您当前的位置：

首页 >

文章列表页 >

Joint Cross-Medium Resource Allocation Algorithm for Dual-mode Communication Systems Based on Heterogeneous Multi-agent Reinforcement Learning

更新时间：2026-09-14

- Joint Cross-Medium Resource Allocation Algorithm for Dual-mode Communication Systems Based on Heterogeneous Multi-agent Reinforcement Learning
- Telecommunications Science (2026)
- 作者机构：
  
  1.华北电力大学燕赵电力实验室，河北保定 071003
  2.华北电力大学电子与通信工程系，河北保定 071003
  3.河北省电力物联网技术重点实验室，河北保定 071003
- 作者简介：
- 基金信息：
  
  S&T Program of Hebei(26364503D);Central Guidance Fund Project for Local Scientific and Technological Development of Hebei Province(264Z2101G)
- DOI：10.11959/j.issn.1000-0801.DXKX260462
  CLC： TN91
- Received：06 July 2026，
  
  Revised：2026-07-28，
  
  Accepted：20 August 2026，
- 稿件说明：
移动端阅览
CHEN Zzhixiong, WEI Zihan. Joint Cross-Medium Resource Allocation Algorithm for Dual-mode Communication Systems Based on Heterogeneous Multi-agent Reinforcement Learning[J/OL]. Telecommunications Science, 2026.
DOI：

CHEN Zzhixiong, WEI Zihan. Joint Cross-Medium Resource Allocation Algorithm for Dual-mode Communication Systems Based on Heterogeneous Multi-agent Reinforcement Learning[J/OL]. Telecommunications Science, 2026. DOI： 10.11959/j.issn.1000-0801.DXKX260462.

摘要

针对低压台区计量网络中双模通信系统信道环境时变、业务需求波动性强、存在通信媒介差异及资源协同调度困难的问题，提出一种基于异构多智能体强化学习的双模通信系统跨媒介资源联合分配方法。基于Lyapunov优化理论将长期队列稳定约束转化为逐时隙在线优化问题，设计了按用户通信模式划分的差异化异构智能体架构，提出了自适应跨媒介资源调控机制，在保障长期队列稳定的前提下，实现了二维资源块与功率在线跨媒介联合分配。仿真结果表明，所提算法在用户供需匹配度(User Supply-demand Ratio

USR)、平均时延和公平性上均优于对比算法，其中USR提升3.5%，平均时延降低8.1%，公平性指数提升1.0%。

Abstract

In the low-voltage distribution area metering network with dual-mode communication

challenges arise from time-varying channel conditions

highly fluctuating service demands

heterogeneous communication media

and difficulty in coordinated resource scheduling. To tackle these issues

we propose a cross-media joint resource allocation method based on heterogeneous multi-agent reinforcement learning. Leveraging Lyapunov optimization

we transform the long-term queue stability constraint into a per-timeslot online optimization problem. A differentiated agent architecture is designed

where agents are categorized according to user communication modes

and an adaptive cross-media resource regulation mechanism is introduced. This enables online joint allocation of two-dimensional resource blocks and transmission power across media while ensuring long-term queue stability. Simulation results demonstrate that the proposed algorithm outperforms baseline schemes in terms of User Supply-demand Ratio(USR)

average delay

and fairness index. Specifically

the USR is improved by 3.5%

the average delay is reduced by 8.1%

and the fairness index is increased by 1.0%.

关键词

Keywords

references

Ribeiro M. V. ， Filomeno M. L. ， Camponogara Â. , et al . Seamless Connectivity：The Power of Integrating Power Line and Wireless Communications [J ] . IEEE Communications Surveys & Tutorials ， 2024 ， 26 ( 1 )： 1 - 40 .

龚钢军，陆俊，熊琛，等．混合业务公平的宽带电力线正交频分复用系统跨层资源分配 [J ] ．中国电机工程学报， 2015 ， 35 ( 6 )： 1390 - 1398 ．

Gong Gangjun , Lu Jun , Xiong Chen , et al . Cross-layer Resource Allocation Based on Mixed-service Fairness for Broadband Power-line OFDM System [J ] . Proceedings of the CSEE ， 2015 ， 35 ( 6 )： 1390 - 1398 ．

陆俊，刘振宇，徐志强，等．计及接入控制策略的宽带电力线OFDM系统跨层资源分配 [J ] ．电网技术， 2016 ， 40 ( 6 )： 1858 - 1866 ．

Lu Jun , Liu Zhenyu , Xu Zhiqiang , et al . Cross-Layer Resource Allocation Considering Access Control for Broadband Power Line OFDM System [J ] . Power System Technology ， 2016 ， 40 ( 6 )： 1858 - 1866 ．

杨挺，何子阳，孙兆帅，等．面向并发多业务的宽带电力线载波通信跨层资源分配算法研究 [J ] ．电网技术， 2021 ， 45 ( 8 )： 3257 - 3267 ．

Yang Ting , He Ziyang , Sun Zhaoshuai , et al . Research on Cross-layer Resource Allocation Algorithm for Concurrent Multi-service in Broadband Power Line Carrier Communication [J ] . Power System Technology ， 2021 ， 45 ( 8 )： 3257 - 3267 ．

Coutinho Y. F. ， Camponogara Â. ， Filomeno M. L. , et al . Two Decades of Research Progress in Resource Allocation for PLC Systems：From Core Concepts to Frontiers [J ] . IEEE Communications Surveys & Tutorials ， 2024 ， 26 ( 3 )： 1710 - 1747 .

Yamakata H. ， Tanigawa Y. ， Tode H . Hybrid OFDMA and CSMA/CA-Based Transmission Strategy for Providing High Throughput and Low Delay in IEEE 802.11ax Wireless LANs [J ] . IEICE Transactions on Communications ， 2025 ，E108-B( 12 )： 1430 - 1442 .

Zhu H. ， Wang J . Chunk-Based Resource Allocation in OFDMA Systems—Part II：Joint Chunk, Power and Bit Allocation [J ] . IEEE Transactions on Communications ， 2012 ， 60 ( 2 )： 499 - 509 .

Jin Y. ， Wang W. ， Zheng Z. , et al . When Average Delay Optimization Meets Deterministic Delay Constraint：A Renewal Framework for Resource Allocation [J ] . IEEE Transactions on Communications ， 2025 ， 73 ( 12 )： 13691 - 13707 .

Wu W. ， Yang Q. ， Li B. , et al . Adaptive Resource Allocation Algorithm of Lyapunov Optimization for Time-Varying Wireless Networks [J ] . IEEE Communications Letters ， 2016 ， 20 ( 5 )： 934 - 937 .

Fan S. ， Zhong Y. ， Hou I . -H., et al. Optimizing Age of Information in Random Access Networks：A Second-Order Approach for Active/Passive Users[J ] . IEEE Transactions on Communications ， 2025 ， 73 ( 1 )： 439 - 453 .

廖晓闽，严少虎，石嘉，等．基于深度强化学习的蜂窝网资源分配算法 [J ] ．通信学报， 2019 ， 40 ( 2 )： 11 - 18 ．

Liao Xiaomin , Yan Shaohu , Shi Jia , et al . Deep reinforcement learning based resource allocation algorithm in cellular networks [J ] . Journal on Communications ， 2019 ， 40 ( 2 )： 11 - 18 ．

Bi S. ， Huang L. ， Wang H. , et al . A. Lyapunov-Guided Deep Reinforcement Learning for Stable Online Computation Offloading in Mobile-Edge Computing Networks [J ] . IEEE Transactions on Wireless Communications ， 2021 ， 20 ( 11 )： 7519 - 7537 .

燕锋，林晓薇，李正浩，等．智能电网中基于多智能体强化学习的频谱分配算法 [J ] ．通信学报， 2023 ， 44 ( 9 )： 12 - 24 ．

Yan Feng , Lin Xiaowei , Li Zhenghao , et al . Spectrum allocation algorithm based on multi-agent reinforcement learning in smart grid [J ] . Journal on Communications ， 2023 ， 44 ( 9 )： 12 - 24 ．

Y. Zhang, D. Guo , " Multi-Agent Reinforcement Learning for Multi-Cell Spectrum and Power Allocation ," in IEEE Transactions on Communications , vol. 73 , no. 8 , pp. 5980 - 5992

Yan Y. ， Zhang B. ， Li C. , et al . Cooperative Caching and Fetching in D2D Communications-A Fully Decentralized Multi-Agent Reinforcement Learning Approach [J ] . IEEE Transactions on Vehicular Technology ， 2020 ， 69 ( 12 )： 16095 - 16109 .

Peng K. ， Ma T. ， Jia L. , et al . Enhancing Collaboration in Heterogeneous Multiagent Systems Through Communication Complementary Graph [J ] . IEEE Transactions on Cybernetics ， 2024 ， 54 ( 11 )： 6881 - 6894 .

Fernandes V. ， Finamore W. A. ， Poor H. V. , et al . The Low-Bit-Rate Hybrid Power Line/Wireless Single-Relay Channel [J ] . IEEE Systems Journal ， 2019 ， 13 ( 1 )： 98 - 109 .

Samir A. ， Elsayed M. ， El-Banna A . A. A., et al. Performance of NOMA-Based Dual-Hop Hybrid Powerline-Wireless Communication Systems[J ] . IEEE Transactions on Vehicular Technology ， 2022 ， 71 ( 6 )： 6548 - 6558 .

Chen Z. ， Zhi L. ， Zhao X. , et al . Parallel Access Scheme for Wireless and Power Line Dual-Connection Communication [J ] . IEEE Transactions on Vehicular Technology ， 2022 ， 71 ( 7 )： 7997 - 8001 .

Filomeno M. L. ， de Campos M . L. R.，Poor H. V., et al. Hybrid Power Line/Wireless Systems：An Optimal Power Allocation Perspective[J ] . IEEE Transactions on Wireless Communications ， 2020 ， 19 ( 10 )： 6289 - 6300 .

Filomeno M. L. ， de Campos M . L. R.，Poor H. V., et al. Hybrid Power Line/Wireless Systems：Power Allocation for Minimizing the Average Bit Error Probability[J ] . IEEE Transactions on Communications ， 2022 ， 70 ( 2 )： 810 - 821 .

Filomeno M. L. ， de Lima V . J. E.，de Campos M. L. R., et al. Hybrid Power Line/Wireless System With Optimal Subcarrier Permutation Under Uniform or Optimal Power Allocation[J ] . IEEE Internet of Things Journal ， 2022 ， 9 ( 23 )： 23915 - 23926 .

陈智雄，刘宗山，金鑫，等．基于协作通信的电力线通信关键技术研究综述 [J ] ．电网技术， 2025 ， 49 ( 4 )： 1668 - 1680 ．

Chen Zhixiong , Liu Zongshan , Jin Xin , et al . Research Review and Prospect of Power Line Communication Technology Based on Collaborative Communication [J ] . Power System Technology ， 2025 ， 49 ( 4 )： 1668 - 1680 ．

HUA M H , TIAN H , WU D B . Hybrid high-speed power line and wireless communication for 5G network [C ] // 2021 International Conference on Space-Air-Ground Computing (SAGC) . 2021 : 124 - 128 .

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

End-to-end throughput evaluation model and optimization method for dual-mode mesh network

Instant power allocation for terahertz NOMA communication networks based on Transformer-double deep Q-network

Resource allocation and power optimization for maritime communication of dual USV based on NOMA

Multi-head graph attention driven feature aggregation for large-scale remote-sening constellation mission planning algorithm

基于M-LAG技术的天翼云专线改造方案

Related Author

SU Zhan

WEN Bo

ZHU Xiaorong

Zhou Yin

Lin Jiongxun

Huang Junkun

Liao Shengtao

She Yuxuan

Related Institution

Nanjing Panda Electronics Co., Ltd.

School of Communication and Information Engineering, Nanjing University of Posts and Telecommunications

Unit of the PLA

South China Academy of Advanced Optoelectronics, South China Normal University

School of Electronic Engineering, Guangxi University of Science and Technology

AI问答

Postal code：100079
Tel：（010）53879206 Email：tmw@bjxintong.com.cn
Technical support is provided by Beijing Founder electronics co., LTD 京ICP备09082226号-64 京公网安备11010602201714号
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰