浏览全部资源
扫码关注微信
电力线载波通信中基于深度学习的信道估计
Deep Learning based Channel Estimation in PLC Communication
- 光通信研究 2024年第2期 页码：22005801-22005808
- 作者机构：
1.重庆邮电大学 通信与信息工程学院，重庆 400065
2.北京智芯微电子科技有限公司，北京 102200
- 作者简介：
敬天成（1995－），男，重庆人。硕士，主要研究方向为通信核心芯片。
段红光，正高级工程师。E-mail：duanhg@cqupt.edu.cn
- 基金信息：国家电网资助项目(ZX-2020BC02-FW14)
DOI：10.13756/j.gtxyj.2024.220058
中图分类号： TN915.853纸质出版日期：2024-04-10，
收稿日期：2023-02-27，
修回日期：2023-03-21，
扫 描 看 全 文
敬天成，段红光，赵旭，等. 电力线载波通信中基于深度学习的信道估计[J].光通信研究，2024(2):220058.
Jing T C, Duan H G, Zhao X, et al. Deep Learning based Channel Estimation in PLC Communication [J]. Study on Optical Communications, 2024(2):220058.
敬天成，段红光，赵旭，等. 电力线载波通信中基于深度学习的信道估计[J].光通信研究，2024(2):220058. DOI： 10.13756/j.gtxyj.2024.220058.
Jing T C, Duan H G, Zhao X, et al. Deep Learning based Channel Estimation in PLC Communication [J]. Study on Optical Communications, 2024(2):220058. DOI： 10.13756/j.gtxyj.2024.220058.
摘要
【目的】
2
电力线载波（PLC）通信系统采用基于帧突发的传输模式，由于PLC系统的收发信机之间存在载波频偏、PLC信道存在各种噪声以及时变特性，加之PLC系统没有专用参考信号，传统信道估计对PLC信道没有跟踪预测能力，进而造成PLC系统性能恶化。
【方法】
2
文章针对现有问题，提出了一种基于长短期记忆（LSTM）神经网络和去噪卷积神经网络（DnCNN）的去噪长短期记忆（DnLSTM）神经网络，并利用该DnLSTM神经网络进行了PLC信道估计。首先对DnLSTM神经网络进行离线训练再保存训练好的DnLSTM参数，之后将其部署到PLC系统中，加载训练完成的参数后再进行在线预测，得到PLC系统信道响应。在电力线系统仿真中，文章采用最小二乘法（LS）、最小均方误差（MMSE）算法以及DnLSTM神经网络进行信道估计，给出在高斯白噪声（AWGN）、组合噪声、色噪声和脉冲噪声条件下的仿真结果，同时调整了用于信道估计的前导符号数量并进行了对应的仿真。
【结果】
2
仿真结果表明，DnLSTM神经网络进行信道估计的精度与采用的前导符号数量有关，采用4个前导符号进行信道估计，其估计精度优于LS，接近MMSE算法，并且DnLSTM神经网络具有很好的抵抗载波频偏以及信道时变的能力。当用于信道估计的前导符号越多时，低信噪比（SNR）情况下的PLC系统性能越好，高SNR情况下的PLC系统性能相似。
【结论】
2
通过以上仿真可得出，基于LSTM和DnCNN的DnLSTM神经网络可以很好地估计存在频偏的PLC系统信道响应，可实时跟踪其变化。
Abstract
【Objective】
2
Power Line Carrier(PLC)communication adopts the frame burst transmission mode. Due to the carrier frequency offset between transceivers
various noise and time-varying characteristics of PLC channel and the system has no dedicated reference signal. The traditional channel estimation has no tracking and prediction ability for the channel
which leads to the deterioration of the PLC system performance.
【Methods】
2
Aiming at the existing problems
this paper proposes a Denoising Long Short Term Memory (DnLSTM) neural network based on Long Short Term Memory (LSTM) neural network and Denoising Convolutional Neural Network (DnCNN)
which is used for PLC channel estimation. First
offline training is performed on DnLSTM and the parameters are saved after training. Then the trained parameters are deployed in PLC system. After loading parameters
online prediction is performed to obtain the predicted PLC system channel estimation. In the simulation of PLC system
this paper uses Least Squares (LS) algorithm
Minimum Mean Square Error (MMSE) algorithm and DnLSTM to estimate the channel response
and gives the simulation results under the conditions of Additive White Gaussian Noise (AWGN)
combined noise
impulsive noise and colored noise. Meanwhile
simulations for different number of preamble symbols for channel estimation are performed.
【Results】
2
The results show that there is a relationship between the accuracy of DnLSTM channel estimation and the number of preamble symbols. Using four preamble symbols for channel estimation
its estimation accuracy is better than LS and close to MMSE algorithm. DnLSTM has a good ability to resist carrier frequency offset and channel time-varying. When the number of preamble symbols for channel estimation increases
PLC system performance with low Singnal to Noise Ratio (SNR) gets better and PLC system performance is similar with high SNR.
【Conclusion】
2
According to simulation results above
it can be concluded that DnLSTM
which is based on DnCNN and LSTM
can predict PLC system channel response with frequency offset very well and it can track the varying PLC system channel response in real time.
关键词
电力线载波通信信道估计深度学习长短期记忆神经网络去噪卷积神经网络
Keywords
PLC communicationchannel estimationdeep learningLSTM neural networkDnCNN
references
王伟, 马草原, 卓孝文. 基于OFDM低压电力线噪声抑制算法研究[J]. 电工技术, 2021(15): 28-31.
Wang W, Ma C Y, Zhuo X W. Research on Low Voltage Power Line Noise Suppression Algorithm based on OFDM[J]. Electric Engineering, 2021(15): 28-31.
金龙, 吴游, 张泳翔. 基于改进SRGAN的OFDM信道估计方法[J]. 计算机与现代化, 2021(10): 112-118.
Jin L, Wu Y, Zhang Y X. OFDM Channel Estimation based on Improved SRGAN[J]. Computer and Modernization, 2021(10): 112-118.
纪勤文, 朱春华. 基于BP神经网络的OFDM系统信道估计[J]. 电讯技术, 2021, 61(7): 793-799.
Ji Q W, Zhu C H. Channel Estimation of OFDM Systems based on BP Neural Network[J]. Telecommunication Engineering, 2021, 61(7): 793-799.
Soltani M, Pourahmadi V, Mirzaei A, et al.Deep Learning-based Channel Estimation[J]. IEEE Communications Letters, 2019, 23(4): 652-655.
常代娜, 周杰. 基于深度学习算法的OFDM信号检测[J]. 东南大学学报(自然科学版), 2020, 50(5): 912-917.
Chang D N, Zhou J. Deep Learning-based Signal Detection in OFDM Systems[J]. Journal of Southeast University (Natural Science Edition), 2020, 50(5): 912-917.
郑建宏, 邓湛. 一种抗脉冲噪声的宽带电力线通信系统信道估计算法[J]. 重庆邮电大学学报(自然科学版), 2019, 31(1): 44-49.
Zheng J H, Deng Z. A Channel Estimation Algorithm for Impulse Noise Suppression in WB-PLC System[J]. Journal of Chongqing University of Posts and Telecommunications (Natural Science Edition), 2019, 31(1): 44-49.
郭丽莎. 基于OFDM的宽带电力线载波通信系统设计[D]. 西安: 西安电子科技大学, 2015.
Guo L S. Design of Broadband Power Line Carrier Communication System based on OFDM[D]. Xi’an: Xidian University, 2015.
Cho Y S, Kim J, Yang W Y, et al. MIMO-OFDM Wireless Communications with MATLAB[M]. USA: Wiley-IEEE Press, 2010.
申敏, 毛文俊, 袁一铭, 等. 基于MIMO电力线信道的定时同步算法[J]. 光通信研究, 2022(2): 18-21.
Shen M, Mao W J, Yuan Y M, et al. Timing Synchronization Method in MIMO Power Line Channel Communications[J]. Study on Optical Communications, 2022(2): 18-21.
石佳琪, 金桂月, 金基宇, 等. 基于深度学习的信道估计[J]. 大连工业大学学报, 2021, 40(5): 367-376.
Shi J Q, Jin G Y, Jin J Y, et al. Channel Estimation based on Deep Learning[J]. Journal of Dalian Polytechnic University, 2021, 40(5): 367-376.
Hochreiter S, Schmidhuber J. Long Short-term Memory[J]. Neural Computation, 1997, 9(8): 1735-1780.
赵越, 许鹏, 蓝晓宇. 基于LSTM网络的OFDM系统信道估计研究与分析[J]. 电脑与信息技术, 2022, 30(2): 49-52.
Zhao Y, Xu P, Lan X Y. Research and Analysis of Channel Estimation of OFDM System based on LSTM Network[J]. Computer and Information Technology, 2022, 30(2): 49-52.
陈成瑞, 孙宁, 何世彪, 等. 面向C-V2X通信的基于深度学习的联合信道估计与均衡算法[J]. 计算机应用, 2021, 41(9): 2687-2693.
Chen C R, Sun N, He S B, et al. Deep Learning-based Joint Channel Estimation and Equalization Algorithm for C-V2X Communications[J]. Journal of Computer Applications, 2021, 41(9): 2687-2693.
Zhang K, Zuo W, Chen Y, et al. Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising[J]. IEEE Transactions on Image Processing: a Publication of the IEEE Signal Processing Society, 2017, 26(7): 3142-3155.
Kingma D P, Ba J. Adam: a Method for Stochastic Optimization[EB/OL]. (2017-01-30)[2023-02-27]. https://arxiv.org/abs/1412.6980.pdfhttps://arxiv.org/abs/1412.6980.pdf.
Canete F J, Cortés J A, Díez L, et al. A Channel Model Proposal for Indoor Power Line Communications[J]. IEEE Communications Magazine, 2011, 49(12): 166-174.
0
浏览量
0
下载量
0
CSCD
- 网络PDF下载
- Meta-XML下载
- BibTeX下载
- Endnote下载
- RefMan 下载
- NoteExpress下载
- NoteFirst下载
关联资源
相关文章
相关作者
相关机构
- 地址：武汉市江夏区高新四路6号烽火科技园4号楼3层 邮编：430205
- 技术支持由北京北大方正电子有限公司提供 鄂ICP备2022010197
鄂公网安备 42011202002092号 - 本系统建议在Chrome、 IE9+ 以上版本浏览器阅读本站内容，360浏览器请切换至极速模式
- Cookies帮助我们提供服务并提供个性化体验。使用本网站，即表示您同意我们使用Cookies
- 总访问量：75199 今日访问量：329