+高级检索
首页 > 过刊浏览>2021年第44卷第3期 >114-119
PDF HTML阅读 XML下载 导出引用 引用提醒
基于图卷积网络的车联网资源管理
作者:
作者单位:

1.上海先进通信与数据科学研究院，2.特种光纤与光接入网重点实验室，3.特种光纤与先进通信国际合作联合实验室，上海大学，上海 200444

中图分类号:

TN929.5

基金项目:

国家重点研发计划资助（2017YFE0121400），国家自然科学基金资助（61501289，61671011，61420106011）


Resource Management of Vehicle Network Based on Graph Convolutional Neural Network
Author:
  • Wang Xiaochang

    Wang Xiaochang

    1.Shanghai Institute for Advanced Communication and Data Science China，2.Key laboratory of Specialty Fiber Optics and Optical Access Networks China,3. Joint International Research Laboratory of Specialty Fiber Optics and Advanced Communication China, Shanghai University, Shanghai 200444
    在期刊界中查找
    在百度中查找
    在本站中查找
  • Zhu Wenxing

    Zhu Wenxing

    1.Shanghai Institute for Advanced Communication and Data Science China，2.Key laboratory of Specialty Fiber Optics and Optical Access Networks China,3. Joint International Research Laboratory of Specialty Fiber Optics and Advanced Communication China, Shanghai University, Shanghai 200444
    在期刊界中查找
    在百度中查找
    在本站中查找
  • Sun Yanzan

    Sun Yanzan

    1.Shanghai Institute for Advanced Communication and Data Science China，2.Key laboratory of Specialty Fiber Optics and Optical Access Networks China,3. Joint International Research Laboratory of Specialty Fiber Optics and Advanced Communication China, Shanghai University, Shanghai 200444
    在期刊界中查找
    在百度中查找
    在本站中查找
  • Wu Yating

    Wu Yating

    1.Shanghai Institute for Advanced Communication and Data Science China，2.Key laboratory of Specialty Fiber Optics and Optical Access Networks China,3. Joint International Research Laboratory of Specialty Fiber Optics and Advanced Communication China, Shanghai University, Shanghai 200444
    在期刊界中查找
    在百度中查找
    在本站中查找
  • Wang Tao

    Wang Tao

    1.Shanghai Institute for Advanced Communication and Data Science China，2.Key laboratory of Specialty Fiber Optics and Optical Access Networks China,3. Joint International Research Laboratory of Specialty Fiber Optics and Advanced Communication China, Shanghai University, Shanghai 200444
    在期刊界中查找
    在百度中查找
    在本站中查找
Affiliation:

1.Shanghai Institute for Advanced Communication and Data Science China，2.Key laboratory of Specialty Fiber Optics and Optical Access Networks China,3. Joint International Research Laboratory of Specialty Fiber Optics and Advanced Communication China, Shanghai University, Shanghai 200444

  • 摘要
    • | |
  • 访问统计
    • |
  • 参考文献
    • |
  • 相似文献
    • |
  • 引证文献
    • | |
  • 文章评论
    摘要:

    车辆到一切（Vehicle-to-Everything，V2X）通信是有效的提高交通安全性和移动性的解决方案。为了解决深度学习在功率分配中存在的需要大量训练数据和泛化性问题，减少车辆网络信道干扰，提出了基于图卷积神经网络(Graph Convolutional Network，GCN)的总用户速率最大化，总用户能效最大化的两种准则下的功率分配框架。所提出的框架首先将无线干扰信道转化为图数据结构，证明了干扰信道的无序性。其次根据不同功率分配准则的特点，构建了GCN网络结构，同时提出相应的损失函数。通过与基于加权最小均方误差（Weighted Minimum mean square error，WMMSE）算法训练的多层感知器(Multilayer Perceptron, MLP)网络对比，仿真数据表明，在小样本训练、可扩展性、可泛化性几个方面，所提出方案优于对比算法。

    Abstract:

    Vehicle to Everything (V2X) communication is an effective solution to improve traffic safety and mobility. In order to solve the problems of deep learning that requires a large amount of training data and generalization in power allocation, this paper proposes a power distribution framework that based on Graph Convolutional Network (GCN) under the three criteria of maximizing the total user rate, maximizing the total user energy efficiency. The proposed framework first converts the wireless interference channel into a graph data structure, which proves the disorder of the interference channel. Secondly, according to the characteristics of different power distribution, the GCN network structure is constructed, and the corresponding loss function is proposed. Compared with the Multilayer Perceptron (MLP) network trained based on the weighted minimum mean square error (WMMSE) algorithm， the simulation data shows that the proposed scheme is better than the comparison algorithm in terms of small sample training, scalability, and generalizability.

    参考文献
    相似文献
    引证文献
引用本文

王晓昌,朱文星,孙彦赞,吴雅婷,王涛.基于图卷积网络的车联网资源管理[J].电子测量技术,2021,44(3):114-119

复制
分享
文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 在线发布日期: 2024-12-19
文章二维码
您是第 位访问者
主管单位：北京电子控股有限责任公司
主办单位：北京无线电技术研究所
地址：北京市东城区北河沿大街79号
电话：13810562337
电子测量技术 ® 2025 版权所有