稀疏隨機(jī)森林下的用電側(cè)異常行為模式檢測(cè)
發(fā)布時(shí)間:2018-01-29 20:12
本文關(guān)鍵詞: 用電側(cè) 異常行為辨識(shí) 隨機(jī)森林 隨機(jī)權(quán)網(wǎng)絡(luò) 稀疏表示 出處:《電網(wǎng)技術(shù)》2017年06期 論文類型:期刊論文
【摘要】:隨著智能電網(wǎng)的不斷推進(jìn)與傳感技術(shù)的高速發(fā)展,我國(guó)電網(wǎng)用電側(cè)數(shù)據(jù)逐步呈現(xiàn)出高復(fù)雜度、高冗余度的冪指數(shù)增長(zhǎng)態(tài)勢(shì)。傳統(tǒng)的用電行為模式檢測(cè)技術(shù)已無(wú)法滿足其分析處理需求。為此提出基于稀疏隨機(jī)森林模型的用電側(cè)異常行為模式檢測(cè)方法。該方法首先利用時(shí)間窗函數(shù)與Bootstrap重采樣,建立用電側(cè)行為模式信息簇。其次,利用基于隨機(jī)權(quán)網(wǎng)絡(luò)的有監(jiān)督學(xué)習(xí)得到隨機(jī)森林模型。最后,對(duì)隨機(jī)森林模型進(jìn)行稀疏化,并依據(jù)異常積累量指標(biāo)判定樣本有無(wú)異常。仿真對(duì)比實(shí)驗(yàn)驗(yàn)證了提出的稀疏隨機(jī)森林模型的精確性與高效性。此外,通過(guò)多種體量數(shù)據(jù)下的Hadoop分布式計(jì)算實(shí)驗(yàn),驗(yàn)證了基于稀疏隨機(jī)森林的用電側(cè)行為模式檢測(cè)方法對(duì)用電側(cè)大數(shù)據(jù)的高效處理能力。
[Abstract]:With the continuous advance of smart grid and the rapid development of sensing technology, the power side data of China's power grid gradually presents a high complexity. The power exponent growth trend of high redundancy. The traditional detection technique of electric behavior pattern can not meet the demand of its analysis and processing. Therefore, a method of detecting abnormal behavior pattern of power side based on sparse stochastic forest model is proposed. The method firstly uses time window function and Bootstrap resampling. Secondly, the supervised learning based on stochastic weight network is used to obtain the stochastic forest model. Finally, the stochastic forest model is sparse. According to the index of abnormal accumulation, the sample is judged to be abnormal or not. The simulation results show that the proposed sparse stochastic forest model is accurate and efficient. The Hadoop distributed computing experiment based on a variety of volume data is carried out to verify the efficient processing ability of the method based on sparse stochastic forest to detect the behavior pattern of the power side of the power side big data.
【作者單位】: 華北電力大學(xué)電氣與電子工程學(xué)院;中國(guó)人民大學(xué)經(jīng)濟(jì)學(xué)院;
【基金】:國(guó)家863高技術(shù)基金項(xiàng)目(2015AA050203)~~
【分類號(hào)】:TM73;TM76
【正文快照】: 權(quán)網(wǎng)絡(luò)的有監(jiān)督學(xué)習(xí)得到隨機(jī)森林模型。最后,對(duì)隨機(jī)森林模型進(jìn)行稀疏化,并依據(jù)異常積累量指標(biāo)判定樣本有無(wú)異常。仿真對(duì)比實(shí)驗(yàn)驗(yàn)證了提出的稀疏隨機(jī)森林模型的精確性與高效性。此外,通過(guò)多種體量數(shù)據(jù)下的Hadoop分布式計(jì)算實(shí)驗(yàn),驗(yàn)證了基于稀疏隨機(jī)森林的用電側(cè)行為模式檢測(cè)方法
【相似文獻(xiàn)】
相關(guān)期刊論文 前2條
1 葉圣永;王曉茹;劉志剛;錢清泉;;基于隨機(jī)森林算法的電力系統(tǒng)暫態(tài)穩(wěn)定性評(píng)估[J];西南交通大學(xué)學(xué)報(bào);2008年05期
2 ;[J];;年期
相關(guān)碩士學(xué)位論文 前2條
1 張興;基于Spark大數(shù)據(jù)平臺(tái)的火電廠節(jié)能分析[D];太原理工大學(xué);2016年
2 楊畢玉;核電站松動(dòng)件檢測(cè)分析研究[D];浙江大學(xué);2016年
,本文編號(hào):1474257
本文鏈接:http://www.sikaile.net/kejilunwen/dianlidianqilunwen/1474257.html
最近更新
教材專著