《電子技術(shù)應(yīng)用》
您所在的位置:首頁 > 電源技術(shù) > 設(shè)計(jì)應(yīng)用 > 基于VMD-LSTM的非侵入式負(fù)荷識(shí)別方法
基于VMD-LSTM的非侵入式負(fù)荷識(shí)別方法
2023年電子技術(shù)應(yīng)用第2期
王毅1,易歡1,李松濃2,馮凌3,劉期烈1,,宋如楠4
1.重慶郵電大學(xué) 通信與信息工程學(xué)院, 重慶 400065,;2.國網(wǎng)重慶市電力公司電力科學(xué)研究院,, 重慶 400014; 3.國網(wǎng)重慶市電力公司營銷服務(wù)中心,,重慶400014,;4.中國電力科學(xué)研究院, 北京100192
摘要: 非侵入式負(fù)荷識(shí)別(Non-Intrusive Load Monitoring,, NILM)技術(shù)僅基于家庭電源總?cè)肟谔幍碾娏?、電壓信息,獲得室內(nèi)電器設(shè)備的電氣信息,。提高負(fù)荷識(shí)別的精度,,對(duì)于優(yōu)化能源結(jié)構(gòu)、提高電能利用效率,、降低能耗,、節(jié)約資源具有重要意義。首先應(yīng)用變分模態(tài)分解(Variational Mode Decomposition,, VMD)對(duì)歸一化的電流信號(hào)分解為K個(gè)IMF分量,,再估計(jì)各個(gè)分量與歸一化電流信號(hào)的相關(guān)系數(shù),挑選相關(guān)系數(shù)最大的兩個(gè)分量作為負(fù)荷特征,,輸入訓(xùn)練好的LSTM神經(jīng)網(wǎng)絡(luò)進(jìn)行識(shí)別,。算例測(cè)試結(jié)果表明,該方法在公開數(shù)據(jù)集PLAID上的識(shí)別率高達(dá)99%,,在實(shí)驗(yàn)室采集的數(shù)據(jù)集上的識(shí)別率為96.6%,,證實(shí)了所提出方法對(duì)提升負(fù)荷識(shí)別精度有顯著效果。
中圖分類號(hào):TM721
文獻(xiàn)標(biāo)志碼:A
DOI: 10.16157/j.issn.0258-7998.223024
中文引用格式: 王毅,,易歡,,李松濃,等. 基于VMD-LSTM的非侵入式負(fù)荷識(shí)別方法[J]. 電子技術(shù)應(yīng)用,,2023,,49(2):127-132.
英文引用格式: Wang Yi,Yi Huan,,Li Songnong,,et al. Non-intrusive load identification method based on VMD-LSTM[J]. Application of Electronic Technique,,2023,49(2):127-132.
Non-intrusive load identification method based on VMD-LSTM
Wang Yi1,,Yi Huan1,,Li Songnong2,F(xiàn)eng Ling3,,Liu Qilie1,,Song Runan4
1.Communication and Information Engineering College, Chongqing University of Posts and Telecommunications,, Chongqing 400067,, China;2.Chongqing Electric Power Research Institute,, Chongqing 400014,, China; 3.Postdoctoral Workstation of the Chongqing Electric Power Corporation,, Chongqing 400014,, China; 4.China Electric Power Research Institute,,Beijing100192,,China
Abstract: Non-intrusive load monitoring (NILM) technology is only based on the current and voltage information of the main entrance of home power supply to obtain the electrical information of indoor electrical equipment. Improving the accuracy of load identification is of great significance to optimize the energy structure, improve the efficiency of power utilization and reduce energy consumption. Firstly, the normalized current signal is decomposed by using variational mode decomposition (VMD), and then the correlation coefficients between each component and the original current signal are calculated. The two components with the largest correlation coefficients are selected as the load characteristics and input into the trained LSTM neural network for identification. The test results of an example show that the recognition rate of this method is up to 99% on public data set PLAID and 96.6% on laboratory data set, which proves the effectiveness of this method.
Key words : variational mode decomposition;smart grid,;LSTM,;correlation coefficient

0 引言

    隨著社會(huì)的發(fā)展,電力成為社會(huì)的主要能源,。電網(wǎng)是電力運(yùn)輸,、分配和使用的載體。保持智能電網(wǎng)的穩(wěn)定運(yùn)行是電力系統(tǒng)規(guī)劃和管理的根本目標(biāo)[1],。負(fù)荷監(jiān)測(cè)可以幫助電力公司獲得用戶的詳細(xì)用電信息,,分析用戶用電信息可以為電力系統(tǒng)的規(guī)劃和智能調(diào)度提供指導(dǎo)意見[2]。對(duì)電力用戶來說,,可以通過負(fù)荷監(jiān)測(cè)結(jié)果分析自己的用電行為,,制定合理的用電策略,降低用電成本,,節(jié)約能源資源,。侵入式負(fù)荷監(jiān)測(cè)(Intrusive Load Monitoring, ILM)和非侵入式負(fù)荷監(jiān)測(cè)(Non-Intrusive Load Monitoring, NILM)是電力監(jiān)控的兩種手段。ILM系統(tǒng)需在每個(gè)家用電器的前端安裝測(cè)量傳感器,,用以實(shí)時(shí)的記錄設(shè)備的用電信息,,其成本與電器的數(shù)量成線性關(guān)系;NILM由美國麻省理工學(xué)院的Hart[3]教授于20世紀(jì)80年代提出,,僅通過家庭入口處的電流電壓信息,,采用算法得到各用電器的電氣信息,。與ILM系統(tǒng)相比,NILM系統(tǒng)有安裝方便,、成本低,、保護(hù)隱私安全等優(yōu)點(diǎn)。非侵入式負(fù)荷識(shí)別主要有兩種實(shí)現(xiàn)方法,,即事件法[4]和分解法[5,,6]。事件法檢測(cè)電器設(shè)備的啟動(dòng)/關(guān)閉事件,,以事件的瞬態(tài)變化為特征判斷電器的類型,,從而推斷電器的實(shí)時(shí)工作狀態(tài),實(shí)現(xiàn)電能的分解,。分解法是直接從多負(fù)載疊加的電氣特性分解為每個(gè)電器特性最可能的組合,。但隨著電器設(shè)備數(shù)量的增多,,分解法的復(fù)雜度大大提高,,而事件法則沒有上述缺點(diǎn)。事件法的關(guān)鍵在于對(duì)電器產(chǎn)生的負(fù)荷投切事件進(jìn)行準(zhǔn)確分類,。




本文詳細(xì)內(nèi)容請(qǐng)下載:http://forexkbc.com/resource/share/2000005183,。




作者信息:

王毅1,易歡1,,李松濃2,,馮凌3,劉期烈1,,宋如楠4

(1.重慶郵電大學(xué) 通信與信息工程學(xué)院,,  重慶 400065;2.國網(wǎng)重慶市電力公司電力科學(xué)研究院,,  重慶 400014,;

3.國網(wǎng)重慶市電力公司營銷服務(wù)中心,重慶400014,;4.中國電力科學(xué)研究院,, 北京100192)




wd.jpg

此內(nèi)容為AET網(wǎng)站原創(chuàng),未經(jīng)授權(quán)禁止轉(zhuǎn)載,。