面向分层异构网络的资源分配:一种稳健分层博弈学习方案
发布时间：2019-05-21 16:06
【摘要】：该文研究了信道状态不确定条件下分层异构微蜂窝网络中的无线资源分配优化问题。首先引入信道不确定模型描述无线信道的随机动态性,并将该问题建模为考虑信道不确定度的双层鲁棒斯坦伯格博弈;然后给出了该博弈的均衡点分析;最后提出了一种分布式改进型分层Q学习方案以实现宏基站和微基站的均衡策略搜索。理论分析和仿真表明,所提出的分层博弈模型可以有效抑制由于信道状态不确定引起的收益下降。所采用的学习方案较传统Q学习方案收敛速度明显加快,更加适用于短时快变的通信环境。
[Abstract]:In this paper, the optimization of wireless resource allocation in layered heterogeneous microcellular networks with uncertain channel state is studied. Firstly, the channel uncertainty model is introduced to describe the stochastic dynamics of wireless channels, and the problem is modeled as a double-layer robust Steinberg game considering channel uncertainty, and then the equilibrium point analysis of the game is given. Finally, a distributed improved hierarchical Q learning scheme is proposed to realize the equilibrium strategy search of macro base station and micro base station. Theoretical analysis and simulation show that the proposed hierarchical game model can effectively suppress the decline of benefits caused by channel state uncertainty. Compared with the traditional Q learning scheme, the convergence speed of the proposed learning scheme is obviously accelerated, and it is more suitable for short-term and rapidly changing communication environment.
【作者单位】： 解放军理工大学通信工程学院;洛阳理工学院;南京电讯技术研究所;解放军信息工程大学信息系统工程学院;
【基金】：国家自然科学基金(61471395,61401508) 江苏省自然科学基金(BK20161125)~~
【分类号】：TN929.5
[Abstract]:In this paper, the optimization of wireless resource allocation in layered heterogeneous microcellular networks with uncertain channel state is studied. Firstly, the channel uncertainty model is introduced to describe the stochastic dynamics of wireless channels, and the problem is modeled as a double-layer robust Steinberg game considering channel uncertainty, and then the equilibrium point analysis of the game is given. Finally, a distributed improved hierarchical Q learning scheme is proposed to realize the equilibrium strategy search of macro base station and micro base station. Theoretical analysis and simulation show that the proposed hierarchical game model can effectively suppress the decline of benefits caused by channel state uncertainty. Compared with the traditional Q learning scheme, the convergence speed of the proposed learning scheme is obviously accelerated, and it is more suitable for short-term and rapidly changing communication environment.
【作者单位】： 解放军理工大学通信工程学院;洛阳理工学院;南京电讯技术研究所;解放军信息工程大学信息系统工程学院;
【基金】：国家自然科学基金(61471395,61401508) 江苏省自然科学基金(BK20161125)~~
【分类号】：TN929.5
【相似文献】
相关期刊论文 前10条
1 陈庆章;组建异构网应着重考虑的问题和产品现状[J];计算机时代;1994年03期
2 汪芸,顾冠群,谢俊清,兑继英,孙昌平;异构网络集成方法研究[J];计算机研究与发展;1997年03期
3 马义忠;杨红旗;高彦;専秋峰;;基于移动Agent异构网络管理的分析与设计[J];微计算机信息;2008年33期
4 黄川;郑宝玉;;多无线电协作技术与异构网络融合[J];中兴通讯技术;2008年03期
5 吴蒙;季丽娜;王X;;无线异构网络的关键安全技术[J];中兴通讯技术;2008年03期
6 李R，
本文编号：2482215
本文链接：https://www.wllwen.com/kejilunwen/xinxigongchenglunwen/2482215.html
