《電子技術(shù)應(yīng)用》
您所在的位置:首頁 > 其他 > 設(shè)計(jì)應(yīng)用 > 基于單分類結(jié)合模糊寬度學(xué)習(xí)的負(fù)荷辨識(shí)方法
基于單分類結(jié)合模糊寬度學(xué)習(xí)的負(fù)荷辨識(shí)方法
2022年電子技術(shù)應(yīng)用第5期
王 毅1,王蕭陽1,李松濃2,陳 濤2,侯興哲2,付秀元3
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.國家電投集團(tuán)數(shù)字科技有限公司,北京100080
摘要: 非侵入式負(fù)荷監(jiān)測(cè)是智能用電的關(guān)鍵技術(shù),有助于加強(qiáng)負(fù)荷側(cè)管理,提高用電效率。隨著電力負(fù)荷類型和數(shù)量的迅速增加,當(dāng)模型中接入訓(xùn)練樣本之外的未知電器時(shí)會(huì)導(dǎo)致模型誤判,降低負(fù)荷識(shí)別的準(zhǔn)確性。為了提高負(fù)荷識(shí)別模型的穩(wěn)定性以及識(shí)別精度,提出一種單分類結(jié)合模糊寬度學(xué)習(xí)的電力負(fù)荷識(shí)別方法。首先,構(gòu)建負(fù)荷特征庫實(shí)現(xiàn)多負(fù)荷識(shí)別;然后,通過單分類K近鄰方法進(jìn)行樣本篩選,排除未知電器的干擾;最后,提出一種基于模糊寬度學(xué)習(xí)系統(tǒng)的負(fù)荷識(shí)別方法解決識(shí)別模型復(fù)雜度高、識(shí)別速率慢的問題。實(shí)驗(yàn)結(jié)果表明,所提出的算法能夠快速有效地識(shí)別電力負(fù)荷。
中圖分類號(hào): TN911.72;TM714
文獻(xiàn)標(biāo)識(shí)碼: A
DOI:10.16157/j.issn.0258-7998.212334
中文引用格式: 王毅,王蕭陽,李松濃,等. 基于單分類結(jié)合模糊寬度學(xué)習(xí)的負(fù)荷辨識(shí)方法[J].電子技術(shù)應(yīng)用,2022,48(5):51-55,60.
英文引用格式: Wang Yi,Wang Xiaoyang,Li Songnong,et al. Load identification method based on one class classification combined with fuzzy broad learning[J]. Application of Electronic Technique,2022,48(5):51-55,60.
Load identification method based on one class classification combined with fuzzy broad learning
Wang Yi1,Wang Xiaoyang1,Li Songnong2,Chen Tao2,Hou Xingzhe2,F(xiàn)u Xiuyuan3
1.Communication and Information Engineering College,Chongqing University of Posts and Telecommunications, Chongqing 400065,China; 2.Chongqing Electric Power Research Institute,Chongqing 400014,China; 3.State Power Investment Group Digital Technology Co.,Ltd.,Beijing 100080,China
Abstract: Non-Intrusive Load Monitoring(NILM) is a key technology for smart electricity consumption, which helps strengthen load-side management and improve electricity efficiency. With the rapid increase of power load types and quantities, when unknown electrical appliances outside the training sample are connected to the model, it will cause the model to misjudge and reduce the accuracy of load identification. In order to improve the stability and accuracy of the load identification model, a power load identification method combining single classification and fuzzy broad learning is proposed. The one-class K-nearest neighbor method is used to screen samples to detect unknown electrical appliances and control the risk of misjudgment. Considering the recognition rate and model complexity, the fuzzy broad learning system is used to classify and recognize the screened samples. The experimental results show that the algorithm proposed in this paper can effectively detect unknown electrical appliances, prevent model misjudgment, and get better results for both single-load and multi-load switching.
Key words : non-intrusive load identification;steady-state feature of load current;fuzzy broad learning system;one class K-nearest neighbor;TS fuzzy syste

0 引言

    電力是推進(jìn)工業(yè)社會(huì)發(fā)展的主要能源之一。在智能電網(wǎng)[1-2]的建設(shè)中,非侵入式負(fù)荷監(jiān)測(cè)(Non-Intrusive Load Monitoring,NILM)[1-2]具有較高的研究價(jià)值和廣闊的應(yīng)用前景。NILM通過用戶負(fù)荷信息挖掘,可以有效緩解能源危機(jī),節(jié)能減耗,提高經(jīng)濟(jì)效益。不同于侵入式方法,NILM技術(shù)通過在主電能輸入端安裝監(jiān)測(cè)設(shè)備來獲取總用電信息從而識(shí)別用戶的負(fù)荷類型和工作狀態(tài),提高了測(cè)量設(shè)備安全性,具有成本低、維護(hù)方便等優(yōu)點(diǎn)。因此,NILM將會(huì)是今后電力測(cè)量方向發(fā)展的主流趨勢(shì),在電力需求側(cè)管理技術(shù)發(fā)展以及智能電網(wǎng)的建設(shè)上具有重要意義。

    非侵入式負(fù)荷識(shí)別方法相比于侵入式方法由于其安裝便利、成本低等特點(diǎn)引起了更多學(xué)者的關(guān)注,取得了較多的研究成果。文獻(xiàn)[3]引入了總諧波失真識(shí)別功率相近的電力負(fù)荷;文獻(xiàn)[4]通過提取負(fù)荷的暫態(tài)特征,計(jì)算貼近度進(jìn)行負(fù)荷識(shí)別,但暫態(tài)特征對(duì)采樣頻率要求較高;文獻(xiàn)[5]采用了V-I軌跡及深度學(xué)習(xí)的方法進(jìn)行負(fù)荷識(shí)別,取得了較好的識(shí)別效果,但高頻數(shù)據(jù)的V-I軌跡計(jì)算量較大;文獻(xiàn)[6]通過將K最鄰近方法與核Fisher判別相結(jié)合,控制誤判風(fēng)險(xiǎn),提高識(shí)別能力及識(shí)別速率;文獻(xiàn)[7]通過提取負(fù)荷的有功功率與無功功率,并采用人工神經(jīng)網(wǎng)絡(luò)的方法進(jìn)行識(shí)別,但識(shí)別率不高。




本文詳細(xì)內(nèi)容請(qǐng)下載:http://ihrv.cn/resource/share/2000004276




作者信息:

王  毅1,王蕭陽1,李松濃2,陳  濤2,侯興哲2,付秀元3

(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.國家電投集團(tuán)數(shù)字科技有限公司,北京100080)




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。