应答式干扰下基于Q学习算法的跳频系统信道调度方法  

A Channel Scheduling Method for Frequency Hopping System Based on Q-learning Algorithm under Reactive Jamming

作　　者：徐长月 黄高明[1] 侯小阳 

机构地区：[1]海军工程大学电子工程学院,武汉430033

出　　处：《电讯技术》2017年第12期1451-1456,共6页Telecommunication Engineering

基　　金：国家自然科学基金资助项目(61601491)

摘　　要：针对应答式干扰对跳频通信的影响,提出了基于Q学习算法的认知无线电跳频系统信道调度模型。该模型根据认知系统对跳频行为的实时回报评估值,运用机器学习的方法寻找出最合理的规避干扰策略,最终达到适应干扰的目的。运用Simulink对该干扰方式下的算法应用性能进行了仿真验证,结果表明该算法能够降低跳频系统此干扰下的误比特率到1%以下,基本接近未受干扰下的误比特率。In response to effect of reactive jamming on frequency hopping（FH） communication,a mode ofcognitive radio frequency hopping system＇s the channel scheduling based on the Q-learning algorithm isproposed. The model uses the method of machine learning to find out the most reasonable strategy of avoi-ding jamming according to the real-time evaluation rewards on hopping behaviors of the cognitive system,and realizes adapting to the jamming eventually. The performance of the application in response to the reac-tive jamming is simulated on Simulink and the results show that it can significantly reduce the bit error rate（BER） of FH system less than one percent which is nearly close to the one in unjammed condition.

关 键 词：认知无线电 跳频系统 应答式干扰 Q学习 信道调度 

分 类 号：TN973.3[电子电信—信号与信息处理]