基于图卷积神经网络的超密集物联网资源分配策略

黄杰; 李幸星; 杨凡; 丁睿杰; 蔡杰良; 姚凤航; 张鑫

doi:10.11959/j.issn.1000-436x.2024178

您当前的位置：

首页 >

文章列表页 >

基于图卷积神经网络的超密集物联网资源分配策略

学术通信 | 更新时间：2024-11-14

- 基于图卷积神经网络的超密集物联网资源分配策略
- Resource allocation strategy for ultra-dense Internet of things based on graph convolutional neural network
- 通信学报 2024年45卷第10期页码：243-252
- 作者机构：
  
  重庆理工大学电气与电子工程学院，重庆 400054
- 作者简介：
  
  [ "黄杰（1988- ），男，重庆人，博士，重庆理工大学副教授，主要研究方向为无线通信理论、通信网络、下一代移动通信技术、认知无线电、无线通信资源分配。" ]
  [ "李幸星（2001- ），男，重庆人，重庆理工大学硕士生，主要研究方向为无线通信理论、无线通信资源分配。" ]
  [ "杨凡（1983- ），男，湖北广水人，博士，重庆理工大学副教授，主要研究方向为无线带宽自适应传输、无线通信网络、下一代移动通信技术、无线通信中的编码技术。" ]
  [ "丁睿杰（2000- ），男，重庆人，重庆理工大学硕士生，主要研究方向为无线带宽自适应传输、无线通信中的编码技术。" ]
  [ "蔡杰良（1998- ），男，重庆人，重庆理工大学硕士生，主要研究方向为无线带宽自适应传输、无线通信中的编码技术。" ]
  [ "姚凤航（2000- ），男，四川泸州人，重庆理工大学硕士生，主要研究方向为无线通信网络、下一代移动通信技术。" ]
  [ "张鑫（2000- ），男，重庆人，重庆理工大学硕士生，主要研究方向为下一代移动通信技术、无线通信资源分配。" ]
- 基金信息：
  
  国家自然科学基金资助项目(62301094);重庆市教育委员会科技研究基金资助项目(KJQN202201157;KJQN202301135);重庆理工大学科研创新团队培育计划基金资助项目(2023TDZ003)
- DOI：10.11959/j.issn.1000-436x.2024178
  中图分类号： TN929.5
- 收稿：2024-06-15，
  
  修回：2024-09-10，
  
  纸质出版：2024-10-25
- 稿件说明：
移动端阅览
黄杰,李幸星,杨凡等.基于图卷积神经网络的超密集物联网资源分配策略[J].通信学报,2024,45(10):243-252.

HUANG Jie,LI Xingxing,YANG Fan,et al.Resource allocation strategy for ultra-dense Internet of things based on graph convolutional neural network[J].Journal on Communications,2024,45(10):243-252.
黄杰,李幸星,杨凡等.基于图卷积神经网络的超密集物联网资源分配策略[J].通信学报,2024,45(10):243-252. DOI： 10.11959/j.issn.1000-436x.2024178.

HUANG Jie,LI Xingxing,YANG Fan,et al.Resource allocation strategy for ultra-dense Internet of things based on graph convolutional neural network[J].Journal on Communications,2024,45(10):243-252. DOI： 10.11959/j.issn.1000-436x.2024178.

摘要

针对超密集物联网（UD-IoT）中存在大量隐藏终端干扰严重影响资源管理问题，提出了一种基于图卷积神经网络的深度确定性梯度的超密集物联网资源分配策略。通过矩阵变换构建冲突图模型，采用极大团和超图理论将冲突图模型转化为冲突超图模型，进而将无冲突资源分配问题转化为超图顶点着色问题，并提出了一种基于图卷积神经网络的深度确定性梯度的超密集物联网资源分配算法，采用图卷积强化学习实现无冲突资源分配和资源复用率最大化。仿真实验表明，所提算法具有更高的资源复用率和吞吐量，可以在超密集物联网中提供更好的性能。

Abstract

To address the significant issue of hidden terminal interference that severely impacted resource management in ultra-dense Internet of things (UD-IoT) environments

a deep deterministic gradient-based conflict-free resource allocation strategy using graph convolution neural network was proposed. The conflict graph model was constructed by employing matrix transformations to represent potential hidden terminal interference among devices. Then

using the concepts of maximal cliques and hypergraph theory

the conflict graph model was transformed into a conflict hypergraph model. This transformation allowed the conflict-free resource allocation problem to be formulated as a hypergraph vertex coloring problem. A deep deterministic gradient-based conflict-free resource allocation algorithm

leveraging graph convolutional neural network reinforcement learning

was developed to achieve conflict-free resource allocation and maximize resource reuse. Simulation results demonstrated that the proposed algorithm achieved higher resource reuse rates and throughput compared to existing methods

providing superior performance in ultra-dense IoT.

关键词

Keywords

references

CHU Z , XIAO P , MI D , et al . IRS-assisted wireless powered IoT network with multiple resource blocks [J ] . IEEE Transactions on Communications , 2023 , 71 ( 4 ): 2335 - 2350 .

LI L X , CHENG Q Q , TANG X , et al . Resource allocation for NOMA-MEC systems in ultra-dense networks: a learning aided mean-field game approach [J ] . IEEE Transactions on Wireless Communications , 2021 , 20 ( 3 ): 1487 - 1500 .

AO S Y , NIU Y , HAN Z , et al . Resource allocation for RIS-assisted device-to-device communications in heterogeneous cellular networks [J ] . IEEE Transactions on Vehicular Technology , 2023 , 72 ( 9 ): 11741 - 11755 .

SARMA S S , HAZRA R , MUKHERJEE A . Symbiosis between D2D communication and industrial IoT for industry 5.0 in 5G mm-wave cellular network: an interference management approach [J ] . IEEE Transactions on Industrial Informatics , 2022 , 18 ( 8 ): 5527 - 5536 .

GBADAMOSI S A , HANCKE G P , ABU-MAHFOUZ A M . Interference avoidance resource allocation for D2D-enabled 5G narrowband Internet of things [J ] . IEEE Internet of Things Journal , 2022 , 9 ( 22 ): 22752 - 22764 .

KIM H M , NGUYEN H V , KANG G M , et al . SWIPT-aided device-to-device communications for massive IoT networks: a novel resource allocation with sparse code multiple access [J ] . IEEE Internet of Things Journal , 2023 , 10 ( 22 ): 19617 - 19629 .

YUAN Y L , YANG T , HU Y L , et al . Two-timescale resource allocation for cooperative D2D communication: a matching game approach [J ] . IEEE Transactions on Vehicular Technology , 2021 , 70 ( 1 ): 543 - 557 .

NAJLA M , BECVAR Z , MACH P . Reuse of multiple channels by multiple D2D pairs in dedicated mode: a game theoretic approach [J ] . IEEE Transactions on Wireless Communications , 2021 , 20 ( 7 ): 4313 - 4327 .

SANUSI I O , NASR K M , MOESSNER K . Radio resource management approaches for reliable device-to-device (D2D) communication in wireless industrial applications [J ] . IEEE Transactions on Cognitive Communications and Networking , 2021 , 7 ( 3 ): 905 - 916 .

YUAN Y Z , LI Z J , LIU Z X , et al . Double deep Q-network based distributed resource matching algorithm for D2D communication [J ] . IEEE Transactions on Vehicular Technology , 2022 , 71 ( 1 ): 984 - 993 .

SEID A M , ERBAD A , ABISHU H N , et al . Multiagent federated reinforcement learning for resource allocation in UAV-enabled Internet of medical things networks [J ] . IEEE Internet of Things Journal , 2023 , 10 ( 22 ): 19695 - 19711 .

SHI Z J , LIU J J . Massive access in 5G and beyond ultra-dense networks: an MARL-based NORA scheme [J ] . IEEE Transactions on Communications , 2023 , 71 ( 4 ): 2170 - 2183 .

SHI D , LI L , OHTSUKI T , et al . Make smart decisions faster: deciding D2D resource allocation via stackelberg game guided multi-agent deep reinforcement learning [J ] . IEEE Transactions on Mobile Computing , 2022 , 21 ( 12 ): 4426 - 4438 .

FAN Q , BAI J N , ZHANG H X , et al . Delay-aware resource allocation in fog-assisted IoT networks through reinforcement learning [J ] . IEEE Internet of Things Journal , 2022 , 9 ( 7 ): 5189 - 5199 .

HUANG J F , YANG Y , GAO Z , et al . Dynamic spectrum access for D2D-enabled Internet of things: a deep reinforcement learning approach [J ] . IEEE Internet of Things Journal , 2022 , 9 ( 18 ): 17793 - 17807 .

BUDHIRAJA I , KUMAR N , TYAGI S . Deep-reinforcement- learning-based proportional fair scheduling control scheme for underlay D2D communication [J ] . IEEE Internet of Things Journal , 2021 , 8 ( 5 ): 3143 - 3156 .

PENG T , GUO Y C , WANG Y C , et al . An interference-oriented 5G radio resource allocation framework for ultradense networks [J ] . IEEE Internet of Things Journal , 2022 , 9 ( 22 ): 22618 - 22630 .

SHAMAEI S , BAYAT S , HEMMATYAR A M A . Interference-aware resource allocation algorithm for D2D-enabled cellular networks using matching theory [J ] . IEEE Transactions on Network and Service Management , 2024 , 21 ( 1 ): 759 - 772 .

HU J M , HENG W , ZHU Y P , et al . Overlapping coalition formation games for joint interference management and resource allocation in D2D communications [J ] . IEEE Access , 2018 , 6 : 6341 - 6349 .

汤小春 , 周佳文 , 田凯飞 , 等 . 大图中全部极大团的并行挖掘算法研究 [J ] . 计算机学报 , 2019 , 42 ( 3 ): 513 - 531 .

TANG X C , ZHOU J W , TIAN K F , et al . An efficient parallel algorithm for maximal clique enumeration in a large graph [J ] . Chinese Journal of Computers , 2019 , 42 ( 3 ): 513 - 531 .

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 X M , YAN S H , SHI J , et al . Deep reinforcement learning based resource allocation algorithm in cellular networks [J ] . Journal on Communications , 2019 , 40 ( 2 ): 11 - 18 .

YANG Y Y , XIE G . Mining maximum matchings of controllability of directed networks based on in-degree priority [C ] // Proceedings of the 2016 35th Chinese Control Conference (CCC) . Piscataway : IEEE Press , 2016 : 1263 - 1267 .

FOSCHINI G J , SALZ J . Digital communications over fading radio channels [J ] . The Bell System Technical Journal , 1983 , 62 ( 2 ): 429 - 456 .

滑思忠 , 丁爱玲 , 郭达伟 , 等 . 基于二分图的D2D通信资源复用分配算法 [J ] . 计算机应用研究 , 2017 , 34 ( 7 ): 2096 - 2098, 2103 .

HUA S Z , DING A L , GUO D W , et al . Resource allocation algorithm in D2D cellular network based on bipartite graph [J ] . Application Research of Computers , 2017 , 34 ( 7 ): 2096 - 2098, 2103 .

浏览量

627

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

智能反射表面辅助的车载边缘任务卸载和资源分配策略

基于深度强化学习的计算卸载与资源分配策略

基于深度强化学习的蜂窝网资源分配算法

基于区域感知的通感算协同网络语义通信可靠性联合优化

Ce³⁺、Tb³⁺在SrZnP₂O₇材料中的发光及能量传递