摘要
多节点协作频谱感知通过融合不同地理位置节点的检测信息,提高了对主用户使用状态的感知性能。但感知性能与感知节点数目之间是非线性关系,感知节点的增加导致能量消耗的增加,而信息量少的节点参与协作感知不利于提高感知性能,反而增加了额外的能量消耗。为提高感知效率,降低能量消耗,提出一种节点选择算法,该算法只调度可信度高的节点参与协作感知,排除性能差的节点参与协作感知,融合中心通过机器学习机制与外部环境不断交互信息,对节点性能进行实时评,及时剔除可靠性下降的节点,动态选择高可靠性的节点参与协作感知,维持高可靠性感知的动态平衡,提高认知网络的鲁棒性。实验结果表明,本文中的算法在6个能耗单位下检测概率可达到99%,在有效降低能量消耗的同时显著提高了感知性能,远优于传统感知方法。
Multi node cooperative spectrum sensing improves the sensing performance of the primary user by fusing the detection information of nodes in different geographical locations.However,there is a nonlinear relationship between the sensing performance and the number of sensing nodes.The increase of sensing nodes leads to the increase of energy consumption,while the nodes with less information participate in cooperative sensing,which is not conducive to improving the sensing performance,but increases the additional energy consumption.In order to improve the sensing efficiency and reduce the energy consumption,a node selection algorithm is proposed.The algorithm only schedules nodes with high reliability to participate in cooperative sensing and excluding nodes with poor performance.The fusion center continuously interacts information with external environment through machine learning mechanism, evaluates the performance of nodes in real time,eliminates nodes with reduced reliability in time,and selects high reliability dynamically In order to maintain the dynamic balance of high reliability perception and improve the robustness of cognitive network,the nodes with high reliability participate in cooperative sensing.The experimental results show that the detection probability of the proposed algorithm can reach 99% under six energy consumption units,which can effectively reduce the energy consumption and significantly improve the sensing performance,which is far better than the traditional sensing methods.
作者
黄堂森
尹向东
李小武
王娜
HUANG Tang-sen;YIN Xiang-dong;LI Xiao-wu;WANG Na(School of Electronics and Information Engineering,Hunan University of Science and Engineering,Yongzhou 425199,China)
出处
《光电子．激光》
EI
CAS
CSCD
北大核心
2020年第7期745-752,共8页
Journal of Optoelectronics·Laser
基金
湖南省自然科学基金项目(2019JJ40097、2019JJ40096)
湖南省永州市科技局项目(2019YZKJ08)
湖南科技学院应用特色学科建设项目资助(湘科院校发[2018]83号)
湖南省教学改革项目:湘教通[2018]436号667
湖南省教育厅青年基金(17B107)
湖南省科技厅重点研究项目(2017NK2390)
永州市科技项目(2019YZKJ10)
湖南省杰出青年基金项目(2020JJ2015)资助项目。
关键词
认知网络
感知节点
机器学习
节点选择
cognitive networks
sensing node
machine learning
node selection
