基于边缘频谱效率的家庭基站无线资源分配算法  

Spectrum allocation based on edge spectral efficiency in Femtocell networks

作　　者：季祥芬[1,2] 朱琦[1,2] 

机构地区：[1]南京邮电大学江苏省无线通信重点实验室 [2]南京邮电大学教育部宽带无线通信与传感网技术重点实验室,江苏南京210003

出　　处：《电路与系统学报》2013年第2期242-247,共6页Journal of Circuits and Systems

基　　金：国家自然科学基金(61171094);国家科学技术重点项目(2011ZX03001-006-02;2011ZX03005-004-03);江苏省自然科学基金重点资助项目(BK2011027)

摘　　要：为了解决日益增长的室内无线资源的需求,近年来人们提出了基于OFDMA系统的家庭基站网络,但是由于OFDMA系统的频谱资源的匮乏,合理使用无线资源改善家庭基站网络的频谱效率成了人们研究的重点。本论文是在基于OFDMA的家庭基站的场景下提出了一种新的基于Q学习的动态信道分配机制,避免了解决复杂的最优化问题。该算法动态地调整各复用系数下的信道数,同时考虑所有家庭基站的频谱效率作为奖赏函数,在尽量保证最低频谱效率的同时提高家庭基站的系统频谱效率。仿真结果表明该算法在满足了家庭基站网络的QoS要求的基础上提高了家庭基站系统的频谱效率。In order to solve the growing requirement of the indoor wireless resource,the femtocell network based on OFDMA system has been proposed in recent years.How to use the limited wireless resource properly and improving the spectral efficiency are two critical problems.In this paper,a new dynamic spectrum allocation scheme for femtocell networks in OFDM scenario based on Q learning is proposed.The proposed algorithm allocates spectrum through Q-Learning dynamically and avoids solving the complex optimization problem.The algorithm adjusts the number of subchannels by different frequency reuse factors.The reward function of Q-Learning contains spectral efficiency of all agents to ensure the lowest spectral efficiency of each cell as much as possible.Simulation results show that the proposed algorithm has improved the spectral efficiency with guaranteed QoS requirements of the femtocell network.

关 键 词：家庭基站网络 Q学习 强化学习 频谱效率 

分 类 号：TN911[电子电信—通信与信息系统]