采用长短期记忆网络与压缩感知实现电物理量轻型化方法
|
摘要
为进一步提升信息化电网性能,提出一种基于长短期记忆网络(LSTM)与压缩感知(CS)实现电物理量轻型化方法。将时间序列变化的电物理量采样数据作为LSTM模型的输入量,稳定结果作为输出量,通过时间反向传播(BPTT)算法训练LSTM模型参数,训练后的模型能充分利用循环架构的特征进行模式识别,并根据LSTM模式识别结果,将信号选择原子库进行CS,来确定测量采样频率。实例结果表明,LSTM+CS方法比常用传统方法采样频率低,传输参数少,可大幅节省存储容量和减轻网络流量。
To further improve the performance of the informationalized power grid,a long-short-term memory(LSTM)network and compressed sensing(CS)method are put forward to realize the lightening of electric physical quantity.The sampled data of time series changes in electrical physical quantities are used as the input of the LSTM model,and the stable results are used as output.LSTM model parameters are trained by back propagation trough time(BPTT)algorithm.After training,the model can make full use of the characteristics of the cyclic structure for pattern recognition.According to LSTM pattern recognition results,the signal selects atom library for CS to determine the measurement sampling frequency.The simulation results show that the LSTM+CS method has lower sampling frequency and less transmission parameters than traditional methods,so it can significantly save storage capacity and reduce the network traffic.
To further improve the performance of the informationalized power grid,a long-short-term memory(LSTM)network and compressed sensing(CS)method are put forward to realize the lightening of electric physical quantity.The sampled data of time series changes in electrical physical quantities are used as the input of the LSTM model,and the stable results are used as output.LSTM model parameters are trained by back propagation trough time(BPTT)algorithm.After training,the model can make full use of the characteristics of the cyclic structure for pattern recognition.According to LSTM pattern recognition results,the signal selects atom library for CS to determine the measurement sampling frequency.The simulation results show that the LSTM+CS method has lower sampling frequency and less transmission parameters than traditional methods,so it can significantly save storage capacity and reduce the network traffic.
引文
[1]赵云.智能电网广域海量电物理量数据轻型传输机理与方法研究[D].武汉:武汉大学,2013.ZHAO Yun.Research on light transmission mechanism and method of wide-area massive electrical and physical data in smart grid[D].Wuhan:Wuhan University,2013.
[2]王阳光.应对灾变的广域保护信息处理及通信技术研究[D].武汉:华中科技大学,2010.WANG Yangguang.Research on information management and communication technology of wide area protection coping with power grid catastrophe[D].Wuhan:Huazhong University of Science&Technology,2010.
[3]张保会.加强继电保护与紧急控制系统的研究提高互联电网安全防御能力[J].中国电机工程学报,2004,24(7):1-6.ZHANG Baohui.Strengthen the protection relay and urgency control systems to improve the capability of security in the interconnected power network[J].Proceedings of the CSEE,2004,24(7):1-6.
[4]ITU-T G.729-1996 coding of speech at 8 kbit/s using conjugate-structure algebraic code excited linear predication(CS-ACELP)[S].1996.
[5]唐炬,董玉林,樊雷,等.基于Hankel矩阵的复小波-奇异值分解法提取局部放电特征信息[J].中国电机工程学报,2015,35(7):1808-1817.TANG Ju,DONG Yulin,FAN Lei,et al.Feature information extraction of partial discharge signal with complex wavelet transform and singular value decomposition based on Hankel matrix[J].Proceedings of the CSEE,2015,35(7):1808-1817.
[6]穆钢,史坤鹏,安军,等.结合经验模态分解的信号能量法及其在低频振荡研究中的应用[J].中国电机工程学报,2008,28(19):36-41.MU Gang,SHI Kunpeng,AN Jun,et al.Signal energy method based on EMD and its application to research of low frequency oscillations[J].Proceedings of the CSEE,2008,28(19):36-41.
[7]丁屹峰,程浩忠,吕干云,等.基于Prony算法的谐波和间谐波频谱估计[J].电工技术学报,2005,20(10):98-101.DING Yifeng,CHENG Haozhong,LGanyun,et al.Spectrum estimation of harmonics and interharmonics based on Prony algorithm[J].Transactions of China Electrotechnical Society,2005,20(10):98-101.
[8]张静,徐政,牛卢璐.TLS-ESPRIT在电力系统信号高精度频谱估计中应用[J].电力自动化设备,2009,29(5):48-51.ZHANG Jing,XU Zheng,NIU Lulu.Application of TLS-ESPRIT in high resolution spectrum estimation of power system signal[J].Electric Power Automation Equipment,2009,29(5):48-51.
[9]闫敬文,刘蕾,屈小波.压缩感知及应用[M].北京:国防工业出版社,2015:7-52.YAN Jingwen,LIU Lei,QU Xiaobo.Compressive sensing and its applications[M].Beijing:National Defend Industry Press,2015:7-52.
[10]王学伟,王琳,苗桂君,等.暂态和短时电能质量扰动信号压缩采样与重构方法[J].电网技术,2012,36(3):191-196.WANG Xuewei,WANG Lin,MIAO Guijun,et al.An approach for compressive sampling and reconstruction of transient and short-time power quality disturbance signals[J].Power System Technology,2012,36(3):191-196.
[11]朱乔木,党杰,陈金富,等.基于深度置信网络的电力系统暂态稳定评估方法[J].中国电机工程学报,2018,38(3):735-743.ZHU Qiaomu,DANG Jie,CHEN Jinfu,et al.A method for power system transient stability assessment based on deep belief networks[J].Proceedings of the CSEE,2018,38(3):735-743.
[12]崔江,唐军祥,龚春英,等.一种无刷发电机旋转整流器自适应故障特征提取方法[J/OL].中国电机工程学报[2017-05-16].http://kns.cnki.net/KCMS/detail/11.2107.TM.20170516.1615.014.html.CUI Jiang,TANG Junxiang,GONG Chunying,et al.An adaptive fault feature extraction method of brushless generator rotating rectifier[J/OL].Proceedings of the CSEE[2017-05-16].http://kns.cnki.net/KCMS/detail/11.2107.TM.20170516.1615.014.html.
[13]赵洪山,刘辉海,刘宏杨,等.基于堆叠自编码网络的风电机组发电机状态监测与故障诊断[J].电力系统自动化,2018,42(11).DOI:10.7500/AEPS20170730001.ZHAO Hongshan,LIU Huihai,LIU Hongyang,et al.Condition monitoring and fault diagnosis of wind turbine generator based on stacked autoencoder network[J].Automation of Electric Power Systems,2018,42(11).DOI:10.7500/AEPS20170730001.
[14]李玉鑑,张婷.深度学习导论及案例分析[M].北京:机械工业出版社,2016:2-6.LI Yujian,ZHANG Ting.Introduction and case analysis of deep learning[M].Beijing:China Machine Press,2016:2-6.
[15]伊恩·古德费洛,约书亚·本吉奥,考维尔·亚伦.深度学习[M].北京:人民邮电出版社,2017:318-348.GOODFELLOW I,BENGIO Y,COURVILLE A.Deep learning[M].Beijing:Posts&Telecom Press,2017:318-348.
[16]白煌.压缩感知系统中字典和感知矩阵优化设计[D].杭州:浙江工业大学,2017.BAI Huang.Optimization of dictionary and sensing matrix for compressed sensing systems[D].Hangzhou:Zhejiang University of Technology,2017.
[17]李峰,郭毅.压缩感知浅析[M].北京:科学出版社,2015.LI Feng,GUO Yi.Analysis of compressed sensing[M].Beijing:Science Press,2015.
[18]汤红忠.基于非相干字典学习及稀疏表示的图像恢复和分类算法研究[D].长沙:湖南大学,2017.TANG Hongzhong.Image restoring and classification based on incoherent dictionary learning and sparse representation[D].Changsha:Hunan University,2017.
[19]鲁铁成.电力系统过电压[M].北京:中国水利水电出版社,2009:55.LU Tiecheng.Overvoltage of power system[M].Beijing:China Water&Power Press,2009:55.
[20]朱德恒,严璋.高电压绝缘[M].北京:清华大学出版社,1992:61.ZHU Deheng,YAN Zhang.High voltage insulation[M].Beijing:Tsinghua University Press,1992:61.
[21]李光琦.电力系统暂态分析[M].3版.北京:中国电力出版社,2007:57.LI Guangqi.Transient analysis of power system[M].3rd ed.Beijing:China Electric Power Press,2007:57.
[22]张磊,黄纯,江亚群,等.应用HS改进原子分解的电能质量扰动辨识分析[J].电网技术,2015,39(1):194-201.ZHANG Lei,HUANG Chun,JIANG Yaqun,et al.Identification analysis of power quality disturbances based on harmony search and atom decomposition[J].Power System Technology,2015,39(1):194-201.
[23]焦李成,杨淑媛,刘芳,等.压缩感知回顾与展望[J].电子学报,2011,39(7):1651-1662.JIAO Licheng,YANG Shuyuan,LIU Fang,et al.Development and prospect of compressive sensing[J].Acta Electronica Sinica,2011,39(7):1651-1662.
[24]彭亚新.求解约束矩阵方程及其最佳逼近的迭代法的研究[D].长沙:湖南大学,2004.PENG Yaxin.The iterative method for the solutions and the optimal approximation of the constrained matrix equation[D].Changsha:Hunan University,2004.
[25]王洪新,贺景亮.电力系统电磁兼容[M].武汉:武汉大学出版社,2004:2.WANG Hongxin,HE Jingliang.EMC of power system[M].Wuhan:Wuhan University Press,2004:2.
[26]潘学萍.电力系统低频振荡[M].北京:中国水利水电出版社,2013:122.PAN Xueping.Low frequency oscillation of power system[M].Beijing:China Water&Power Press,2013:122.
[27]张大波,刘志刚,张亚军.复小波研究现状及其在电力系统中的应用进展[J].电力系统自动化,2006,30(17):97-104.ZHANG Dabo,LIU Zhigang,ZHANG Yajun.Complex wavelet transform review and its applications in power system[J].Automation of Electric Power Systems,2006,30(17):97-104.
[2]王阳光.应对灾变的广域保护信息处理及通信技术研究[D].武汉:华中科技大学,2010.WANG Yangguang.Research on information management and communication technology of wide area protection coping with power grid catastrophe[D].Wuhan:Huazhong University of Science&Technology,2010.
[3]张保会.加强继电保护与紧急控制系统的研究提高互联电网安全防御能力[J].中国电机工程学报,2004,24(7):1-6.ZHANG Baohui.Strengthen the protection relay and urgency control systems to improve the capability of security in the interconnected power network[J].Proceedings of the CSEE,2004,24(7):1-6.
[4]ITU-T G.729-1996 coding of speech at 8 kbit/s using conjugate-structure algebraic code excited linear predication(CS-ACELP)[S].1996.
[5]唐炬,董玉林,樊雷,等.基于Hankel矩阵的复小波-奇异值分解法提取局部放电特征信息[J].中国电机工程学报,2015,35(7):1808-1817.TANG Ju,DONG Yulin,FAN Lei,et al.Feature information extraction of partial discharge signal with complex wavelet transform and singular value decomposition based on Hankel matrix[J].Proceedings of the CSEE,2015,35(7):1808-1817.
[6]穆钢,史坤鹏,安军,等.结合经验模态分解的信号能量法及其在低频振荡研究中的应用[J].中国电机工程学报,2008,28(19):36-41.MU Gang,SHI Kunpeng,AN Jun,et al.Signal energy method based on EMD and its application to research of low frequency oscillations[J].Proceedings of the CSEE,2008,28(19):36-41.
[7]丁屹峰,程浩忠,吕干云,等.基于Prony算法的谐波和间谐波频谱估计[J].电工技术学报,2005,20(10):98-101.DING Yifeng,CHENG Haozhong,LGanyun,et al.Spectrum estimation of harmonics and interharmonics based on Prony algorithm[J].Transactions of China Electrotechnical Society,2005,20(10):98-101.
[8]张静,徐政,牛卢璐.TLS-ESPRIT在电力系统信号高精度频谱估计中应用[J].电力自动化设备,2009,29(5):48-51.ZHANG Jing,XU Zheng,NIU Lulu.Application of TLS-ESPRIT in high resolution spectrum estimation of power system signal[J].Electric Power Automation Equipment,2009,29(5):48-51.
[9]闫敬文,刘蕾,屈小波.压缩感知及应用[M].北京:国防工业出版社,2015:7-52.YAN Jingwen,LIU Lei,QU Xiaobo.Compressive sensing and its applications[M].Beijing:National Defend Industry Press,2015:7-52.
[10]王学伟,王琳,苗桂君,等.暂态和短时电能质量扰动信号压缩采样与重构方法[J].电网技术,2012,36(3):191-196.WANG Xuewei,WANG Lin,MIAO Guijun,et al.An approach for compressive sampling and reconstruction of transient and short-time power quality disturbance signals[J].Power System Technology,2012,36(3):191-196.
[11]朱乔木,党杰,陈金富,等.基于深度置信网络的电力系统暂态稳定评估方法[J].中国电机工程学报,2018,38(3):735-743.ZHU Qiaomu,DANG Jie,CHEN Jinfu,et al.A method for power system transient stability assessment based on deep belief networks[J].Proceedings of the CSEE,2018,38(3):735-743.
[12]崔江,唐军祥,龚春英,等.一种无刷发电机旋转整流器自适应故障特征提取方法[J/OL].中国电机工程学报[2017-05-16].http://kns.cnki.net/KCMS/detail/11.2107.TM.20170516.1615.014.html.CUI Jiang,TANG Junxiang,GONG Chunying,et al.An adaptive fault feature extraction method of brushless generator rotating rectifier[J/OL].Proceedings of the CSEE[2017-05-16].http://kns.cnki.net/KCMS/detail/11.2107.TM.20170516.1615.014.html.
[13]赵洪山,刘辉海,刘宏杨,等.基于堆叠自编码网络的风电机组发电机状态监测与故障诊断[J].电力系统自动化,2018,42(11).DOI:10.7500/AEPS20170730001.ZHAO Hongshan,LIU Huihai,LIU Hongyang,et al.Condition monitoring and fault diagnosis of wind turbine generator based on stacked autoencoder network[J].Automation of Electric Power Systems,2018,42(11).DOI:10.7500/AEPS20170730001.
[14]李玉鑑,张婷.深度学习导论及案例分析[M].北京:机械工业出版社,2016:2-6.LI Yujian,ZHANG Ting.Introduction and case analysis of deep learning[M].Beijing:China Machine Press,2016:2-6.
[15]伊恩·古德费洛,约书亚·本吉奥,考维尔·亚伦.深度学习[M].北京:人民邮电出版社,2017:318-348.GOODFELLOW I,BENGIO Y,COURVILLE A.Deep learning[M].Beijing:Posts&Telecom Press,2017:318-348.
[16]白煌.压缩感知系统中字典和感知矩阵优化设计[D].杭州:浙江工业大学,2017.BAI Huang.Optimization of dictionary and sensing matrix for compressed sensing systems[D].Hangzhou:Zhejiang University of Technology,2017.
[17]李峰,郭毅.压缩感知浅析[M].北京:科学出版社,2015.LI Feng,GUO Yi.Analysis of compressed sensing[M].Beijing:Science Press,2015.
[18]汤红忠.基于非相干字典学习及稀疏表示的图像恢复和分类算法研究[D].长沙:湖南大学,2017.TANG Hongzhong.Image restoring and classification based on incoherent dictionary learning and sparse representation[D].Changsha:Hunan University,2017.
[19]鲁铁成.电力系统过电压[M].北京:中国水利水电出版社,2009:55.LU Tiecheng.Overvoltage of power system[M].Beijing:China Water&Power Press,2009:55.
[20]朱德恒,严璋.高电压绝缘[M].北京:清华大学出版社,1992:61.ZHU Deheng,YAN Zhang.High voltage insulation[M].Beijing:Tsinghua University Press,1992:61.
[21]李光琦.电力系统暂态分析[M].3版.北京:中国电力出版社,2007:57.LI Guangqi.Transient analysis of power system[M].3rd ed.Beijing:China Electric Power Press,2007:57.
[22]张磊,黄纯,江亚群,等.应用HS改进原子分解的电能质量扰动辨识分析[J].电网技术,2015,39(1):194-201.ZHANG Lei,HUANG Chun,JIANG Yaqun,et al.Identification analysis of power quality disturbances based on harmony search and atom decomposition[J].Power System Technology,2015,39(1):194-201.
[23]焦李成,杨淑媛,刘芳,等.压缩感知回顾与展望[J].电子学报,2011,39(7):1651-1662.JIAO Licheng,YANG Shuyuan,LIU Fang,et al.Development and prospect of compressive sensing[J].Acta Electronica Sinica,2011,39(7):1651-1662.
[24]彭亚新.求解约束矩阵方程及其最佳逼近的迭代法的研究[D].长沙:湖南大学,2004.PENG Yaxin.The iterative method for the solutions and the optimal approximation of the constrained matrix equation[D].Changsha:Hunan University,2004.
[25]王洪新,贺景亮.电力系统电磁兼容[M].武汉:武汉大学出版社,2004:2.WANG Hongxin,HE Jingliang.EMC of power system[M].Wuhan:Wuhan University Press,2004:2.
[26]潘学萍.电力系统低频振荡[M].北京:中国水利水电出版社,2013:122.PAN Xueping.Low frequency oscillation of power system[M].Beijing:China Water&Power Press,2013:122.
[27]张大波,刘志刚,张亚军.复小波研究现状及其在电力系统中的应用进展[J].电力系统自动化,2006,30(17):97-104.ZHANG Dabo,LIU Zhigang,ZHANG Yajun.Complex wavelet transform review and its applications in power system[J].Automation of Electric Power Systems,2006,30(17):97-104.