史建超;胡正伟;贺冬梅;谢志远;

• 1:华北电力大学电气与电子工程学院

摘要(Abstract)：

提出了一种基于深度学习的电力线信道传输特性识别方法,通过人工智能方法完成对电力线信道传输特性的识别。传统的信道传输特性识别一般采用信道估计方法,该方法在噪声较大时估计效果不理想。所提方法采用去噪自编码器能有效对噪声进行抑制,可以在噪声较强的环境下实现信道传输特性的正确识别。在实际应用中,针对自编码器神经网络去噪后数据存在背景效应的问题,提出使用颜色调整方法进一步滤除干扰,提高了对去噪样本的识别成功率。基于深度学习框架建立了仿真模型,分析了9类基准传输样本的信道传输特性识别效果。仿真结果表明,该方法能够在不同的神经网络模型中以及多种噪声条件下,完成对电力线信道传输特性的识别,对进一步完善电力线通信质量保障具有重要意义。

关键词(KeyWords)： 电力线通信;泛在电力物联网;深度学习;传输特性识别;人工智能;卷积神经网络

Abstract:

Keywords:

基金项目(Foundation): 河北省自然科学基金项目(E2019502186);; 河北省科技计划项目(17211704D)~~

作者(Author): 史建超;胡正伟;贺冬梅;谢志远;

Email:

DOI: 10.13335/j.1000-3673.pst.2019.1527

参考文献(References)：

• [1] Cano C,Pittolo A,Malone D,et al.State of the art in power line communications:from the applications to the medium[J].IEEE Journal on Selected Areas inCommunications, 2016, 34(7):1935-1952.
• [2]王毅，陈启鑫，张宁，等．5G通信与泛在电力物联网的融合：应用分析与研究展望．电网技术，2019,43(5):1575-1585.Wang Yi,Chen Qixin,Zhang Ning,et al.Fusion of the 5G communication and the ubiquitous electric internet of things:application analysis and research prospects[J]. Power System Technology,2019,43(5):1575-1585(in Chinese).
• [3]曹旺斌，尹成群，谢志远，等，宽带MIMO-PLC随机参数信道建模与特性．电网技术，2017,41(3):1029-1034.Cao Wangbin,Yin Chengqun,Xie Zhiyuan,et al.Modeling and analysis of broadband MIMO-PLC random parameter channels[J].Power System Technology,2017,41(3):1029-1034(in Chinese).
• [4] Elgenedy M,Sayed M,Al-Dhahir N,et al.Cyclostationary noise mitigation for SIMO power line communications[J].IEEE Access,2018(6):5460-5484.
• [5] Piante M D, Tonello A M. On impedance matching in a power-line-communication system[J].IEEE Transactions on Circuits and Systems II:Express Briefs,2016,63(7):653-657.
• [6] Canale S,Giorgio A D,Lanna A,et al.Optimal planning and routing in medium voltage power line communications networks[J].IEEE Transactions on Smart Grid,2013.4(2):711-719.
• [7] Cheng X,Liu D J,Wang C,et al.Deep learning-based channel estimation and equalization scheme for FBMC/OQAM systems[J].IEEE Wireless Communications Letters,2019,8(3):881-884.
• [8] Ye H,Li G Y,Juang B H.Power of deep learning for channel estimation and signal detection in OFDM systems[J].IEEE Wireless Communications Letters,2018,7(1):114-117.
• [9] Yang Y W,Gao F F,Ma X L,et al.Deep learning-based channel estimation for doubly selective fading channels[J].IEEE Access,2019(7):36579-36589.
• [10] Guo J B,Wang Z J,LüH F,et al.Transmission characteristics of low-voltage distribution networks in China and its model[J].IEEE Transactions on Power Delivery,2005,20(2):1341-1348.
• [11]刘海涛，张保会，郑涛．低压电网信道频率响应模型的研究[J]．电工技术学报，2004,19(11):66-71.Liu Haitao,Zhang Baohui,Zheng Tao.Research on frequency model of low-voltage network channel[J]. Transactions of China Electrotechnical Society,2004,19(11):66-71(in Chinese).
• [12] Zimmermann M,Dostert K.A multipath model for the power line channel[J].IEEE Transactions on Communications,2002,50(4):553-559.
• [13] Ferreira HC,Lampe L,Newbury J,et al.Power line communications:theory and applications for narrowband and broadband communications over power lines[M].New York,USA:John Wiley and Sons Publication,2010.
• [14]赵志勇．电力线信道特性分析及FPGA硬件实现[D]．西安：西安电子科技大学，2014.
• [15] Wen L,Li X Y,Gao L,et al.A new convolutional neural network-based data-driven fault diagnosis method[J]. IEEE Transactions on Industrial Electronics,2018,65(7):5990-5998.
• [16] Yang H Y,Wang F Y.Wireless network intrusion detection based on improved convolutional neural network[J].IEEE Access,2019(7):64366-64374.
• [17] Simonyan K,Zisserman A.Very deep convolutional networks for large-scale image recognition[C]//International Conference on Learning Representations.San Diego,CA,USA:the Computational and Biological Learning Society,2014:1409-1423.
• [18] Hammad I,El-Sankary K.Impact of approximate multipliers on VGG Deep learning network[J].IEEE Access,2018(6):60438-60444.
• [19] Najafipour A, Babaee A, Shahrtash S M. Comparing the trustworthiness of signal-to-noise ratio and peak signal-to-noise ratio in processing noisy partial discharge signals[J]. IET Science,Measurement and Technology,2013,7(2):112-118.
• [20] Rumelhart DE, Hinton G E, Williams R J. Learning internal representations by error-propagation[J]. Readings in Cognitive Science,1988,323(6088):399-421.
• [21] Kang Y,Lee K T,Eun J,et al.Stacked denoising autoencoders for face pose normalization[J]. Neural Information Processing,2013(8228):241-248.
• [22]张春辉．基于自编码器的稀疏深度模型的研究与应用[D]．西安：西安电子科技大学，2017.
• [23] Glorot X,Bengio Y.Understanding the difficulty of training deep feedforward neural networks[J]. Journal of Machine Learning Research,2010(9):249-256.