基于長短期記憶網(wǎng)絡的風電場發(fā)電功率超短期預測
發(fā)布時間：2018-07-26 17:12
【摘要】：精確的風電場發(fā)電功率超短期預測對電力系統(tǒng)的經(jīng)濟調(diào)度和安全穩(wěn)定運行意義重大。為充分利用多數(shù)據(jù)源中的有效信息來進一步提高風電場超短期發(fā)電功率的預測精度,提出了一種基于長短期記憶(long short-term memory,LSTM)網(wǎng)絡的多變量風電場超短期發(fā)電功率預測方法。該方法首先利用距離分析法篩選出與風電功率相關程度高的變量,進而降低數(shù)據(jù)的規(guī)模和復雜程度。然后利用LSTM網(wǎng)絡對多變量時間序列進行動態(tài)時間建模,最終實現(xiàn)對風電功率的預測。采用美國加州某風電場的實測數(shù)據(jù)進行驗證,結(jié)果表明,文中方法能夠有效利用多變量時間序列進行風電場發(fā)電功率的超短期預測,較人工神經(jīng)網(wǎng)絡和支持向量機擁有更高的預測精度。
[Abstract]:The accurate short-term prediction of wind power generation power is of great significance to the economic dispatch and safe and stable operation of the power system. In order to make full use of the effective information in the multi data source to further improve the prediction accuracy of the ultra short term power generation power of the wind farm, a kind of long short-term memory (LSTM) network based on the long and short period memory is proposed. This method first uses distance analysis method to select variables with high correlation with wind power, and then reduces the scale and complexity of the data, then uses LSTM network to model the dynamic time series of multivariable time series, and finally realizes the prediction of wind power. The measured data of a wind farm in the state are verified. The results show that the method can effectively use the multivariable time series to predict the power generation power of the wind farm effectively, and has a higher prediction accuracy than the artificial neural network and the support vector machine.
【作者單位】： 強電磁工程與新技術國家重點實驗室(華中科技大學);國網(wǎng)湖南省電力公司經(jīng)濟技術研究院;國網(wǎng)湖北省電力公司經(jīng)濟技術研究院;
【基金】：國家重點研發(fā)計劃項目(2016YFB0900100)~~
【分類號】：TM614
[Abstract]:The accurate short-term prediction of wind power generation power is of great significance to the economic dispatch and safe and stable operation of the power system. In order to make full use of the effective information in the multi data source to further improve the prediction accuracy of the ultra short term power generation power of the wind farm, a kind of long short-term memory (LSTM) network based on the long and short period memory is proposed. This method first uses distance analysis method to select variables with high correlation with wind power, and then reduces the scale and complexity of the data, then uses LSTM network to model the dynamic time series of multivariable time series, and finally realizes the prediction of wind power. The measured data of a wind farm in the state are verified. The results show that the method can effectively use the multivariable time series to predict the power generation power of the wind farm effectively, and has a higher prediction accuracy than the artificial neural network and the support vector machine.
【作者單位】： 強電磁工程與新技術國家重點實驗室(華中科技大學);國網(wǎng)湖南省電力公司經(jīng)濟技術研究院;國網(wǎng)湖北省電力公司經(jīng)濟技術研究院;
【基金】：國家重點研發(fā)計劃項目(2016YFB0900100)~~
【分類號】：TM614
【相似文獻】
相關期刊論文 前10條
1 劉士榮;李松峰;寧康紅;周嘯波;榮延澤;;基于極端學習機的光伏發(fā)電功率短期預測[J];控制工程;2013年02期
2 劉士榮;李松峰;寧康紅;周嘯波;榮延澤;;基于極端學習機的光伏發(fā)電功率短期預測[J];控制工程;2013年03期
3 王麗婕;廖曉鐘;高陽;高爽;;風電場發(fā)電功率的建模和預測研究綜述[J];電力系統(tǒng)保護與控制;2009年13期
4 田麗;鄧閱;;聯(lián)合條件下風力發(fā)電風速預測[J];安徽工程大學學報;2012年03期
5 盧靜;翟海青;劉純;王曉蓉;;光伏發(fā)電功率預測統(tǒng)計方法研究[J];華東電力;2010年04期
6 徐星;張虹;樂海洪;徐敏;;采用氣象信息的神經(jīng)網(wǎng)絡應用于短期風力發(fā)電功率預測[J];南昌大學學報(工科版);2011年01期
7 阿碧;;身背核電站移民外星[J];發(fā)明與創(chuàng)新(綜合科技);2011年11期
8 許昌;李e，
本文編號：2146709
本文鏈接：http://sikaile.net/kejilunwen/dianlidianqilunwen/2146709.html
最近更新
教材專著
