基于OS-ELM的宽带电力线通信解映射优化算法  

Optimization algorithm for de-mapping module of broadband power line communication based on OS-ELM

作　　者：谢文旺 孙云莲[1] Xie Wenwang;Sun Yunlian(School of Electric Engineering and Automation,Wuhan University,Wuhan 430072,China)

机构地区：[1]武汉大学电气与自动化学院

出　　处：《电测与仪表》2019年第13期1-6,50,共7页Electrical Measurement & Instrumentation

摘　　要：针对传统信道估计技术会降低通信系统有效性的缺陷,提出了一种基于在线序贯极限学习机(OS-ELM)的宽带PLC解映射优化算法,用以提高宽带电力线通信系统的通信质量。以我国广东省某小区用户电能表的实际采集数据作为原始数据,搭建了宽带电力线通信系统仿真模型,在实测的500m四径信道下进行仿真测试并与BP神经网络以及传统的ELM进行性能对比和比较分析。试验结果表明,在各种不同信噪比的通信环境下,引入OS-ELM均表现出更快的训练速度和更好的抗干扰特性。除去信噪比过低的极端恶劣的通信环境以外,该算法均可以有效提高通信质量,降低误码率。Aiming at the limitation that the traditional channel estimation technology will reduce the effectiveness of communication system,a broadband PLC de-mapping optimization algorithm based on the online sequential limit learning machine(OS-ELM)is proposed to improve the communication quality of the broadband PLC system.The simulation model of broadband power line communication system is built with the actual data collected from a cell user of electric meter in Guangdong province.The simulation model is carried out under the measured 500 m four-path channel and compared with the BP neural network and the traditional ELM.The test results show that the introduction of OS-ELM shows faster training speed and better anti-interference characteristics under various communication environments with different SNR.Except for the extremely poor communication environment with low SNR,the algorithm can effectively improve the communication quality and reduce the bit error rate.

关 键 词：电力线通信 OFDM OS-ELM 解映射 误码率 

分 类 号：TM933[电气工程—电力电子与电力传动]