基于LSTM与注意力机制的卫星透明转发器频率干扰规避方法  被引量:1

A Method for Avoiding Frequency Interference in Satellite Transparent Transponders Based on LSTM and Attention Mechanism

在线阅读下载全文

作  者:班亚明 王宝宝 孙文宇 付垒朋 刘秀芳 贾慧燕 BAN Yaming;WANG Baobao;SUN Wenyu;FU Leipeng;LIU Xiufang;JIA Huiyan(Academy for Network and Communications of CETC,Shijiazhuang 050081,China;Shijiazhuang Military Representative Office of the Military Representative Bureau of the Equipment Department of the Aerospace System Center,Shijiazhuang 050081,China)

机构地区:[1]中国电科网络通信研究院,河北石家庄050081 [2]航天系统部装备部军事代表局驻石家庄军事代表室,河北石家庄050081

出  处:《无线电工程》2023年第9期2211-2216,共6页Radio Engineering

摘  要:针对卫星通信系统中的透明转发器频率资源干扰问题,设计了基于LSTM的卫星透明转发器频率干扰规避方法。通过LSTM+Attention模型识别频率干扰类别并进行分层处置,同时实现了将长期和短期频率干扰规避相结合的优化策略。策略利用载波监视采样的卫星频谱干扰信息,通过运控、网管和网控系统进行干扰处置,实验结果表明,该方法有效降低了网络的可分资源受扰率的同时提高了正常可用资源量。该干扰规避策略具有实时性高、受扰率低、可有效提高资源利用效率的优势。To deal with the frequency resource interference problem of transparent transponders in satellite communication system,an LSTM-based frequency interference avoidance method for satellite transparent transponders is designed.The LSTM+Attention model is used to identify frequency interference categories and perform hierarchical disposal,and at the same time realize an optimization strategy that combines long-term and short-term frequency interference avoidance.The strategy utilizes the satellite spectrum interference information sampled by carrier monitoring to deal with the interference through the operation control,network management and network control systems.Experimental results show that this method effectively reduces the interference rate of the separable resources of the network and increases the amount of normal available resources.The interference avoidance strategy has the advantages of high real-time performance,low interference rate,and can effectively improve resource utilization efficiency.

关 键 词:干扰规避 LSTM 注意力机制 透明转发器 卫星通信 

分 类 号:TN927[电子电信—通信与信息系统]

 

参考文献:

正在载入数据...

 

二级参考文献:

正在载入数据...

 

耦合文献:

正在载入数据...

 

引证文献:

正在载入数据...

 

二级引证文献:

正在载入数据...

 

同被引文献:

正在载入数据...

 

相关期刊文献:

正在载入数据...

相关的主题
相关的作者对象
相关的机构对象