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.
出处
《电路与系统学报》
北大核心
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)
关键词
家庭基站网络
Q学习
强化学习
频谱效率
femtocell networks
Q-Learning
interference management
spectral efficiency
