基于Q-Learning算法的毫微微小区功率控制算法  

Power Control Algorithm Based on Q-Learning in Femtocell

作　　者：李云[1] 唐英 刘涵霄 LI Yun;TANG Ying;LIU Hanxiao(Chongqing Key Laboratory of Mobile Communication Technology,The Chongqing University of Posts and Telecommunications,Chongqing 400065,China)

机构地区：[1]重庆邮电大学移动通信技术重庆市重点实验室

出　　处：《电子与信息学报》2019年第11期2557-2564,共8页Journal of Electronics & Information Technology

基　　金：国家自然科学基金(61671096);重庆市研究生科研创新项目(CYS17220);重庆市“科技创新领军人才支持计划”(CSTCCXLJRC201710);重庆市基础科学与前沿技术研究项目(cstc2017jcyjBX0005);重庆市留学人员创业创新支持计划~~

摘　　要：该文研究macro-femto异构蜂窝网络中移动用户的功率控制问题,首先建立了以最小接收信号信干噪比为约束条件,最大化毫微微小区的总能效为目标的优化模型;然后提出了基于Q-Learning算法的毫微微小区集中式功率控制(PCQL)算法,该算法基于强化学习,能在没有准确信道状态信息的情况下,实现对小区内所有用户终端的发射功率统一调整。仿真结果表明该算法能实现对用户终端的功率有效控制,提升系统能效。The power control problem of mobile users in macro-femto heterogeneous cellular networks is studied.Firstly,an optimization model that maximizes the total energy efficiency of femtocells with the minimum received signal-to-noise ratio as the constraint is established.Then,a femtocell centralized Power Control algorithm based on Q-Learning(PCQL)is proposed.Based on reinforcement learning,the algorithm can adjust the transmit power of the user terminal without accurate channel state information simultaneously.The simulation results show that the algorithm can effectively control the power of the user terminal and improve system energy efficient.

关 键 词：集中式功率控制 Q-Learning算法 能效优化 

分 类 号：TN92[电子电信—通信与信息系统]