基于聚类算法的叠加星座图可见光通信系统  

Superimposed Constellation Visible Light Communication System Based onClustering Algorithm

作　　者：闫卿 YAN Qing(Unit 91977 of PLA,Beijing 100036,China)

机构地区：[1]中国人民解放军91977部队,北京100036

出　　处：《通信技术》2024年第3期255-260,共6页Communications Technology

摘　　要：简述了利用叠加星座图调制的方法来解决可见光多输入多输出通信系统容易受高信道相干性影响的问题,同时探究了机器学习中的聚类算法,以降低系统的误码率,提高通信传输的可靠性。研究结果表明,当星座图因受到非线性效应影响而发生旋转时,与不加入任何算法的系统相比,采用了K-means和模糊C均值算法的通信系统的误码率有了大幅度的下降,且不会受到旋转角度的影响。此外,对比分析2种聚类算法发现,K-means的原理和运算过程相对而言更加简便,可以更好地提高数据传输速率,提供更可靠安全的通信传输。The method of using superimposed constellation modulation to solve the problem that visible light multi-input multi-output communication system susceptible to high channel coherence is briefly described.Meanwhile,clustering algorithms in machine learning are explored to reduce the BER(Bit Error Rate)of the system and improve the reliability of communication transmission.The simulation results indicate that when the constellation is rotated due to nonlinear effects,compared with the system without any algorithms,the BER of the communication system using K-means and FCM(Fuzzy C-Means)algorithms is greatly reduced,and the system is not affected by the rotation angle.In addition,by comparing and analyzing these two clustering algorithms,it is found that the principle and operation process of K-means are relatively simpler,which can better improve the data transmission rate and provide more reliable and secure communication transmission.

关 键 词：叠加星座图 可见光通信 多输入多输出 聚类算法 误码率 

分 类 号：TN929.12[电子电信—通信与信息系统]