基于分簇协同Q-学习的频谱感知算法

Algorithm of Spectrum Sensing Based on Clustering Cooperative Q-learning

针对大规模认知无线电网络中协同频谱感存在的感知时间长、能量消耗过多、缺乏自适应能力等问题,提出了一种基于分簇协同的Q-学习频谱感知算法.该算法利用分簇机制,把大规模的环境变成小规模的簇内环境,分簇后簇内采用协同Q-学习,通过代理在与环境交互过程中不断试错来确定频谱检测的最佳门限值,使系统具有自主学习的能力.实验结果表明:大规模环境下系统的检测性能有显著提高.

Due to long sensing time, excess energy consuming and incapability of adaptive, this paper proposes a algorithm of spectrum sensing based on clustering cooperative Q-learning in large-scale cognitive radios systems. The algorithm uses cluster mechanism ,divided the large-scale environment into small ones, using the collaborative q-learning in the divided clusters. Obtain the optimal threshold of spectrum detection by continuous processes of ＂trial and error＂ in the interaction between agents and environment . Through this way, the system will have the ability of autonomous learning. The experimental results show that the detection performance of system improved significantly.