基于混合神经网络的电力线脉冲噪声参数估计方法  

Parameter Estimation Method Based on Mixed Neural Networks for Impulsive Noise in Power Line Communications

作　　者：王飞杨 刘祖军[1] 孙德春[1] 王琨 WANG Feiyang;LIU Zujun;SUN Dechun;WANG Kun(ISN State Key Laboratory,Xidian University,Xi’an 710000,Shaanxi Province,China;State Grid Xian Power Supply Company,Xi’an 710000,Shaanxi Province,China)

机构地区：[1]西安电子科技大学综合业务网国家重点实验室,陕西省西安市710000 [2]国网西安供电公司,陕西省西安市710000

出　　处：《电力信息与通信技术》2023年第8期1-7,共7页Electric Power Information and Communication Technology

基　　金：国家自然科学基金项目(62171345)。

摘　　要：脉冲噪声广泛存在于电力线通信(power line communication,PLC)系统中,会严重影响系统的通信性能。电力线脉冲噪声的建模通常使用α稳定分布模型,为达到最佳的脉冲噪声抑制效果,需要知道脉冲噪声的类型和相关参数。为此,文章提出一种基于混合神经网络的符合α稳定分布的脉冲噪声参数估计方法。不同于传统的方法,本方法可以分别独立地估计α稳定分布的重要参数α(即特征指数)和γ(即尺度参数)。仿真结果表明,与传统方法相比,提出的方法具有更准确的参数估计性能,归一化均方误差值仅为10–4左右。Impulsive noise is a widespread phenomenon in power line communications(PLC),which will seriously affect the communication performance.The power line impulsive noise is typically modelled asαstable distribution.To achieve the best impulsive noise mitigation,we need to know the type and parameters of impulsive noise.Therefore,this paper proposes a mixed neural network to implement the parameter estimation for the impulsive noise in power line communications consistent withαstable distribution.Different from the traditional methods,the proposed method can seperately estimate the important parameterα(i.e.,index of stability)andγ(i.e.,scale parameter).The simulation results show that,compared with the traditional methods,the proposed method can achieve more accurate parameter estimation performance with the normalized mean squared error of 10^(–4).

关 键 词：电力线通信 脉冲噪声 Α稳定分布 参数估计 混合神经网络 

分 类 号：TN915.853[电子电信—通信与信息系统]