發(fā)布時間：2018-08-05 10:19

【摘要】：針對動態(tài)神經(jīng)網(wǎng)絡(luò)風(fēng)電功率預(yù)測模型輸入變量較多、模型復(fù)雜的問題,將神經(jīng)網(wǎng)絡(luò)和平均影響值方法相結(jié)合,提出了一種基于神經(jīng)網(wǎng)絡(luò)平均影響值的超短期風(fēng)電功率預(yù)測方法。此方法綜合考慮了各輸入變量對輸出變量(風(fēng)電預(yù)測功率)的外部貢獻(xiàn)率和內(nèi)部貢獻(xiàn)率,篩選出了對輸出變量貢獻(xiàn)率最大的輸入變量,建立了一個優(yōu)化的神經(jīng)網(wǎng)絡(luò)超短期風(fēng)電功率預(yù)測模型。實(shí)驗結(jié)果表明,所提模型降低了預(yù)測模型的復(fù)雜度,減少了測量噪聲對預(yù)測精度的影響,得到了較好的風(fēng)電功率預(yù)測結(jié)果。
[Abstract]:In order to solve the problem that the wind power prediction model of dynamic neural network has many input variables and complex model, a super-short-term wind power prediction method based on the average influence value of neural network is proposed by combining the neural network with the average influence value method. In this method, the external and internal contribution rates of the input variables to the output variables (wind power prediction power) are considered synthetically, and the input variables with the largest contribution to the output variables are selected. An optimized neural network model for predicting ultra-short-term wind power is established. The experimental results show that the proposed model reduces the complexity of the prediction model and reduces the influence of measurement noise on the prediction accuracy.
【作者單位】： 中國能源建設(shè)集團(tuán)廣東省電力設(shè)計研究院有限公司;南瑞集團(tuán)公司(國網(wǎng)電力科學(xué)研究院);國電南瑞南京控制系統(tǒng)有限公司;
【基金】：國家高技術(shù)研究發(fā)展計劃(863計劃)資助項目(2013AA050601)~~
【分類號】：TM614;TP183

【相似文獻(xiàn)】

相關(guān)期刊論文 前10條

1 王雪峰,鄔建華,馮英浚,王建元;運(yùn)用樣本更新的實(shí)時神經(jīng)網(wǎng)絡(luò)進(jìn)行短期電力負(fù)荷預(yù)測[J];系統(tǒng)工程理論與實(shí)踐;2003年04期

2 文漢云;;硫化氫燃燒的神經(jīng)網(wǎng)絡(luò)PID控制及其仿真[J];自動化與儀器儀表;2006年01期

3 張U，

本文編號：2165488