基于DNN的低复杂度联合解调译码迭代同步算法  

Low-complexity iterative synchronization algorithm incorporating DNN for joint demodulation decoding

作　　者：崔永生 詹亚锋[1] 陈泰伊 方鑫 CUI Yongsheng;ZHAN Yafeng;CHEN Taiyi;FANG Xin(Beijing National Research Center for Information Science and Technology,Tsinghua University,Beijing 100084,China;Department of Electronic Engineering,Tsinghua University,Beijing 100084,China;Electric Power Research Institute,State Grid Jiangsu Electric Power Co.,Ltd.,Nanjing 210024,China)

机构地区：[1]清华大学北京信息科学与技术国家研究中心,北京100084 [2]清华大学电子工程系,北京100084 [3]国网江苏省电力有限公司电力科学研究院,江苏南京210024

出　　处：《系统工程与电子技术》2024年第11期3893-3900,共8页Systems Engineering and Electronics

基　　金：国家电网公司科技项目(5400-202255158A-1-1-ZN)资助课题。

摘　　要：在无线通信的诸多场景,如卫星通信、深空通信和隐蔽通信中,受限于发射功率、传输距离等因素,接收信号非常微弱。现有联合解调译码迭代同步算法,将信道编码增益作用于信号接收全过程,可有效降低接收机的同步门限,但是计算复杂度较高。利用迭代接收目标函数的形态一致特性,提出一种基于深度神经网络(deep neural network,DNN)的同步优化策略。该策略与传统的迭代同步方法相比,可在1e-5误码率下降低24%的计算复杂度。这一研究成果为迭代接收技术在更高数据速率场景下的工程应用提供了新的发展方向,同时展现出深度学习在解决复杂通信环境问题中的潜力。In many wireless communication scenarios,including satellite communication,deep space communication,and covert communication,the received signal is markedly weak due to inherent limitations in factors such as transmission power and transmission distance.The existing joint demodulation decoding iterative synchronization algorithm applies channel coding gain to the entire signal reception process,which can effectively reduce the synchronization threshold of the receiver,but the computational complexity is high.This paper makes use of the morphological consistency characteristics of the iterative received target function and puts forward a synchronization optimization strategy based on deep neural network(DNN).In comparison to traditional iterative synchronization methods,this strategy can reduce computational complexity by 24%at a bit error rate of 1e-5.This research provides a new direction for the engineering application of iterative reception technology in higher data rate scenarios,while demonstrating the potential of deep learning in addressing complex communication environment issues.

关 键 词：联合解调译码 迭代同步 深度神经网络 最大似然估计 

分 类 号：TN927[电子电信—通信与信息系统]