《電子技術(shù)應(yīng)用》
您所在的位置:首頁(yè) > 電源技術(shù) > 設(shè)計(jì)應(yīng)用 > 基于諧波分量與有效值的神經(jīng)網(wǎng)絡(luò)負(fù)荷分解
基于諧波分量與有效值的神經(jīng)網(wǎng)絡(luò)負(fù)荷分解
2022年電子技術(shù)應(yīng)用第8期
蔡雨露,聶玉虎,崔文朋,鄭 哲,劉 瑞,池穎英
北京智芯微電子科技有限公司,北京100192
摘要: 非侵入式負(fù)荷分解可以從主表電流變化信息中分解出各個(gè)用電器的用電信息,方便為用電戶(hù)提供更精細(xì)化、有針對(duì)性的用電管理和調(diào)度服務(wù)。當(dāng)前利用一維卷積的非侵入式負(fù)荷分解算法存在分解準(zhǔn)確率不高、新增用戶(hù)用電器需要重新訓(xùn)練、復(fù)雜度較高的問(wèn)題?;诖?,利用電流有效值和傅里葉變換后的諧波分量信息,提出一種基于一維卷積神經(jīng)網(wǎng)絡(luò)的負(fù)荷分解算法,利用相似性對(duì)比分解出各個(gè)用電器電流信息,解決了新增用戶(hù)或用電器需要重新訓(xùn)練的問(wèn)題。經(jīng)實(shí)驗(yàn)發(fā)現(xiàn),所提出的方法還可以在一定程度上提高負(fù)荷分解的準(zhǔn)確率,且復(fù)雜度較低。
中圖分類(lèi)號(hào): TN911
文獻(xiàn)標(biāo)識(shí)碼: A
DOI:10.16157/j.issn.0258-7998.211760
中文引用格式: 蔡雨露,聶玉虎,崔文朋,等. 基于諧波分量與有效值的神經(jīng)網(wǎng)絡(luò)負(fù)荷分解[J].電子技術(shù)應(yīng)用,2022,48(8):123-126.
英文引用格式: Cai Yulu,Nie Yuhu,Cui Wenpeng,et al. Non-intrusive residential electricity load disaggregation based on harmonic components and effective value[J]. Application of Electronic Technique,2022,48(8):123-126.
Non-intrusive residential electricity load disaggregation based on harmonic components and effective value
Cai Yulu,Nie Yuhu,Cui Wenpeng,Zheng Zhe,Liu Rui,Chi Yingying
Beijing Smart-Chip Microelectronics Technology Co.,Ltd.,Beijing 100192,China
Abstract: Non-intrusive load decomposition can decompose the electricity consumption information of each consumer from the current change information of the main meter, which is convenient for providing electricity consumers with more refined and targeted electricity management and dispatching services. The current non-intrusive load decomposition algorithm using one-dimensional convolution has the problems that the decomposition accuracy is not high, the new user appliances need to be retrained, and the complexity is high. Based on this, this paper uses the effective value of current and the harmonic component information after Fourier transform to propose a load decomposition algorithm based on one-dimensional convolutional neural network, which uses similarity comparison to decompose the current information of each consumer, and solves the new problem that increasing users or using electrical appliances requires retraining. It is found through experiments that the method proposed in this paper can also improve the accuracy of load decomposition to a certain extent, and the complexity is low.
Key words : non-intrusive load decomposition;convolutional neural network;smart gridword

0 引言

    非侵入式負(fù)荷監(jiān)測(cè)(Non-Intrusive Load Monitoring,NILM)也稱(chēng)為非入侵式負(fù)荷分解(Non-Intrusive Load Disaggregation,NILD)[1],其通過(guò)對(duì)某一特定區(qū)域的總電表數(shù)據(jù)進(jìn)行分析,可獲取該范圍內(nèi)各用電負(fù)荷的相關(guān)信息,如負(fù)荷的數(shù)量、各負(fù)荷的類(lèi)別、所處工作狀態(tài)以及對(duì)應(yīng)的能耗使用情況等[2]。NILM可以在不入戶(hù)、不對(duì)用戶(hù)用電器分別安裝電表的前提下,實(shí)現(xiàn)對(duì)用戶(hù)用電情況的監(jiān)測(cè),通過(guò)用電行為分析更精準(zhǔn)為用戶(hù)提供相應(yīng)的用電服務(wù)[3],對(duì)提高供電服務(wù)水平、節(jié)省電能資源、提高用電效率等都有重要的現(xiàn)實(shí)意義。

    1980年,Hart[4]開(kāi)創(chuàng)性地提出NILM的概念,所提出的監(jiān)控器在電源接口處進(jìn)行測(cè)量,基于對(duì)總負(fù)載的電流和電壓的詳細(xì)分析來(lái)確定在電負(fù)載中打開(kāi)和關(guān)閉的單個(gè)設(shè)備的能耗。這種方法可以將用電器從少量電器種類(lèi)中分解出來(lái),對(duì)于用電器種類(lèi)較多的情況下,則很難準(zhǔn)確地進(jìn)行分解。因此,后續(xù)不斷有學(xué)者提出通過(guò)增加不同負(fù)荷特征的方式改進(jìn)分解效果。負(fù)荷特征主要包括有穩(wěn)態(tài)特征、暫態(tài)特征、周期性特征狀態(tài)轉(zhuǎn)換特征,其中暫態(tài)特征又可以細(xì)分為暫態(tài)功率波形特征、電壓噪聲特征等,穩(wěn)態(tài)特征細(xì)分為功率的階躍特征、穩(wěn)態(tài)電流波形特征等[5]。通過(guò)研究發(fā)現(xiàn),通過(guò)提取更多特征的方式進(jìn)行負(fù)荷分解取得了良好的分解效果。




本文詳細(xì)內(nèi)容請(qǐng)下載:http://ihrv.cn/resource/share/2000004664。




作者信息

蔡雨露,聶玉虎,崔文朋,鄭  哲,劉  瑞,池穎英

(北京智芯微電子科技有限公司,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。