摘要
为了提高宽带电力线通信系统的通信质量,基于宽带电力线通信系统的基本原理,构建了宽带电力线通信系统的仿真模型。以广东云浮某小区用户电表的实际采集数据作为原始数据,在500 m的四径信道模型下,分别引入了BP神经网络和Elman神经网络进行了通信质量的仿真测试。针对神经网络算法普遍存在的抗噪声性能差的缺点,提出一种基于改进VPGA优化的Elman神经网络用于电力线通信系统解映射模块的数据处理,并进行了仿真测试。实验结果表明,该算法不占用宝贵的频谱资源且实现方便,并且除去信号被噪声淹没等极端恶劣的信道环境以外,均可以显著提高宽带电力线通信系统的通信质量,降低误码率。
In order to improve the communication quality of the broadband power line communication system and based on the basic principle of the broadband power line communication system,a simulation model of the broadband power line communication system is built.Taking the actual data collected from a district user’s electric meter in Yunfu of Guangdong Province as the original data,the BP neural network and Elman neural network are introduced to the simulation test of the communication quality under the 500 m four-path channel model.Aiming at the disadvantage of poor anti-noise performance of neural network algorithms,an Elman neural network based on improved VPGA optimization is proposed for the data processing of the de-mapping module of power line communication system,and the simulation test is carried out.Experimental results show that the algorithm does not occupy valuable spectrum resources and is convenient to implement.Except the extreme bad channel environment,the algorithm can significantly improve the communication quality of the broadband power line communication system and reduce the bit error rate.
作者
谢文旺
孙云莲
易仕敏
王华佑
徐冰涵
XIE Wenwang;SUN Yunlian;YI Shimin;WANG Huayou;XU Binghan(School of Electric Engineering and Automation,Wuhan University,Wuhan 430072,China;Guangdong Power Grid Co.,Ltd.,Guangzhou 510620,China)
出处
《电力系统保护与控制》
EI
CSCD
北大核心
2019年第6期58-65,共8页
Power System Protection and Control
基金
南方电网公司科技项目资助(035300KK52150007)~~
