通信学报 ›› 2023, Vol. 44 ›› Issue (8): 215-227.doi: 10.11959/j.issn.1000-436x.2023148

• 学术通信 • 上一篇    

6G密集网络中基于深度强化学习的资源分配策略

杨凡, 杨成, 黄杰, 张仕龙, 喻涛, 左迅, 杨川   

  1. 重庆理工大学电气与电子工程学院，重庆 400054
  • 修回日期:2023-07-10 出版日期:2023-08-01 发布日期:2023-08-01
  • 作者简介: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宽带自适应传输、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等
    杨成（1999- ），男，重庆人，重庆理工大学硕士生，主要研究方向为无线宽带物理层、智能物理层技术等
    黄杰（1988- ），男，重庆人，博士，重庆理工大学讲师，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、无线通信资源分配等
    张仕龙（1996- ），男，河北保定人，重庆理工大学硕士生，主要研究方向为无线通信资源分配、下一代移动通信等
    喻涛（1999- ），男，重庆人，重庆理工大学硕士生，主要研究方向为认知无线电和无线通信资源分配
    左迅（1998- ），男，重庆人，重庆理工大学硕士生，主要研究方向为下一代无线通信技术、无线自组网技术等
    杨川（1999- ），男，重庆人，重庆理工大学硕士生，主要研究方向为无线通信网络、无线通信接入技术等
  • 基金资助:
    国家自然科学基金资助项目(62301094);重庆市自然科学基金资助项目(cstc2021jcyj-msxmX0251);重庆市教育委员会科学技术研究计划基金资助项目(KJQN202101115);重庆市教育委员会科学技术研究计划基金资助项目(KJQN202201157);重庆市教育委员会科学技术研究计划基金资助项目(KJQN202301135);重庆理工大学国家自然科学基金和社会科学基金培育计划资助项目(2022PYZ017);重庆市巴南区科技基金资助项目(KY202208153976019);重庆理工大学科研创新团队培育计划基金资助项目(2023TDZ003);重庆理工大学研究生教育高质量发展行动计划基金资助项目(gzlcx20233076)

Resource allocation strategy based on deep reinforcement learning in 6G dense network

Fan YANG, Cheng YANG, Jie HUANG, Shilong ZHANG, Tao YU, Xun ZUO, Chuan YANG   

  1. School of Electrical and Electronic Engineering, Chongqing University of Technology, Chongqing 400054, China
  • Revised:2023-07-10 Online:2023-08-01 Published:2023-08-01
  • Supported by:
    The National Natural Science Foundation of China(62301094);The Natural Science Foundation of Chongqing(cstc2021jcyj-msxmX0251);The Science and Technology Research Program of Chongqing Education Commission of China(KJQN202101115);The Science and Technology Research Program of Chongqing Education Commission of China(KJQN202201157);The Science and Technology Research Program of Chongqing Education Commission of China(KJQN202301135);The Cultivation Plan of National Natural Science Foundation and Social Science Foundation of Chongqing University of Technology(2022PYZ017);Chongqing Banan District Scientific Research Project(KY202208153976019);The Cultivation Program of Scientific Research and Innovation Team of Chongqing University of Technology(2023TDZ003);The Funding Result of Graduate Education High-quality Development Action Plan of Chongqing University of Technology(gzlcx20233076)

在线阅读

33

PDF下载

301

摘要：

6G 密集网络（DN）中通过资源分配实现小区间无交叠干扰是提升网络性能的重要技术，但资源受限和节点密集分布使其很难通过传统的优化方法解决资源分配问题。针对此问题，建立了基于点线图染色的交叠干扰模型，将深度强化学习（DRL）和交叠干扰模型相结合，提出一种基于竞争深度Q网络（Dueling DQN）的资源分配方法。该方法利用交叠干扰模型与资源复用率设计即时奖励，利用Dueling DQN自主学习生成6G DN资源分配策略，实现小区间无交叠干扰的资源分配。仿真实验表明，所提方法可有效提高网络吞吐量和资源复用率，提升网络性能。

关键词: 6G密集网络, 交叠干扰, 深度Q网络, 资源分配

Abstract:

In order to realize no overlapping interference between cells, 6G dense network (DN) adopting resource allocation is the important technology of enhancing network performance.However, limited resources and dense distribution of nodes make it difficult to solve the problem of resource allocation through traditional optimization methods.To tackle the problem, a point-line graph coloring based overlapping interference model was formulated and a Dueling deep Q-network (DQN) based resource allocation method was proposed, which combined deep reinforcement learning (DRL) and the overlapping interference model.Specifically, the proposed method adopted the overlapping interference model and resource reuse rate to design the immediate reward.Then, generating 6G DN resource allocation strategies were independently learned by using Dueling DQN to achieve the goal of realizing resource allocation without overlapping interference between cells.The performance evaluation results show that the proposed method can effectively increase both network throughput and resource reuse rate, as well as enhance network performance.

Key words: 6G dense network, overlapping interference, deep Q-network, resource allocation

中图分类号: 

No Suggested Reading articles found!