Suzhou Electric Appliance Research Institute
期刊號(hào)： CN32-1800/TM| ISSN1007-3175

Article retrieval

文章檢索

首頁(yè) >> 文章檢索 >> 文章瀏覽排名

風(fēng)電功率及其預(yù)測(cè)誤差概率分布研究

來(lái)源：電工電氣發(fā)布時(shí)間：2021-09-18 13:18 瀏覽次數(shù)：539

風(fēng)電功率及其預(yù)測(cè)誤差概率分布研究

謝彥祥
(中國(guó)電力工程顧問(wèn)集團(tuán)西南電力設(shè)計(jì)院有限公司，四川 成都 610021)
 
    摘 要：進(jìn)行風(fēng)電功率及其預(yù)測(cè)誤差概率分布研究對(duì)分析風(fēng)電功率分布特性有重要意義。以風(fēng)電功率、日功率波動(dòng)量均值為指標(biāo)，統(tǒng)計(jì)分析風(fēng)電在不同時(shí)間尺度下的波動(dòng)概率分布；針對(duì)正態(tài)分布模 型對(duì)風(fēng)電功率及其預(yù)測(cè)誤差分布擬合效果較差問(wèn)題，利用非參數(shù)估計(jì)法擬合風(fēng)電功率及其短期預(yù)測(cè)誤差概率分布，并以殘差平方和、相關(guān)系數(shù)為評(píng)價(jià)指標(biāo)，對(duì)比不同預(yù)測(cè)模型和采樣間隔對(duì)應(yīng)的擬合效果；基于實(shí)測(cè)數(shù)據(jù)的分析結(jié)果表明，非參數(shù)估計(jì)法可以有效擬合風(fēng)電功率及其短期預(yù)測(cè)誤差概率分布，且具有較好的實(shí)用性。
    關(guān)鍵詞：風(fēng)電功率；概率分布；短期預(yù)測(cè)；預(yù)測(cè)誤差分布；非參數(shù)估計(jì)
    中圖分類號(hào)：TM614     文獻(xiàn)標(biāo)識(shí)碼：A     文章編號(hào)：1007-3175(2021)09-0007-07
 
Study on Probability Distribution of Wind Power and Its Forecasting Error
 
XIE Yan-xiang
（Southwest Electric Power Design Institute Co., Ltd. of CPECC, Chengdu 610021, China）
 
    Abstract: The investigation of the distribution of wind power and its prediction error probability is necessary. It has a significant meaning to the analysis of wind power distribution characteristics. In this paper, the average value of wind power and daily power fluctuations were used as indicators to statistically analyze the probability distribution of wind power fluctuations on different time scales. The normal distribution model has problems of poor-fitting effect on wind power and prediction error distribution. This study used a non-parametric estimation method to fit wind power and its short-term prediction error probability distribution. It also used the residual sum of squares and correlation coefficient as evaluation indicators to compare the fitting effects of different prediction models and sampling intervals. The analysis result based on the measured data shows that the non-parametric estimation method can effectively fit the probability distribution of wind power and its short-term forecast error, and it has well practicability.
    Key words: wind power; probability distribution; short-term forecast; forecast error distribution; non-parametric estimation
 
參考文獻(xiàn)
[1] 王利寧，彭天鐸，向征艱，等. 碳中和目標(biāo)下中國(guó)能源轉(zhuǎn)型路徑分析[J] . 國(guó)際石油經(jīng)濟(jì)，2021，29(1) ：2-8.
[2] ELKJæR L G, HORST M, NYBORG S.Identities,innovation, and governance: A systematic review of co-creation in wind energy transitions[J].Energy Research & Social Science，2021，71 ：101834.
[3] LV Jiaqing , ZHENG Xiaodong , PAWLAK M ,et al. Very short-term probabilistic wind power prediction using sparse machine learning and nonparametric density estimation algorithms[J].Renewable Energy，2021，177 ：181-192.
[4] 萬(wàn)筱鐘，康耀元，呼斯樂(lè)，等. 西北地區(qū)風(fēng)電功率波動(dòng)特性概率密度及波動(dòng)統(tǒng)計(jì)[J] . 電網(wǎng)與清潔能源，2021，37(4) ：107-115.
[5] LIN Zi, LIU Xiaolei, MAURIZIO C.Wind power prediction based on high-frequency SCADA data along with isolation forest and deep learning neural networks[J].International Journal of Electrical Power and Energy Systems，2020，18(6) ：34-41.
[6] LI Lijuan, LI Yuan, ZHOU Bin, et al.An adaptive time-resolution method for ultra short-term wind power prediction [J] .International Journal of Electrical Power and Energy Systems，2020，27(1) ：123-131.
[7] 楊茂，馬劍，李成鳳，等. 風(fēng)電功率波動(dòng)特性的混合 Logistic 分布模型[J] . 電網(wǎng)技術(shù)，2017，41(5) ：1376-1382.
[8] 丁華杰，宋永華，胡澤春，等. 基于風(fēng)電場(chǎng)功率特性的日前風(fēng)電預(yù)測(cè)誤差概率分布研究[J] . 中國(guó)電機(jī)工程學(xué)報(bào)，2013，33(34) ：136-144.
[9] 王錚，王偉勝，劉純，等. 基于風(fēng)過(guò)程方法的風(fēng)電功率預(yù)測(cè)結(jié)果不確定性估計(jì)[J] . 電網(wǎng)技術(shù)，2013，37(1) ：242-247.
[10] 萬(wàn)書亭，萬(wàn)杰. 基于量化指標(biāo)和概率密度分布的風(fēng)電功率波動(dòng)特性研究[J] . 太陽(yáng)能學(xué)報(bào)，2015，36(2) ：362-367.
[11] 楊茂，杜剛，齊玥，等. 基于概率統(tǒng)計(jì)的風(fēng)電功率波動(dòng)規(guī)律性分析[J] . 太陽(yáng)能學(xué)報(bào)，2015，36(9) ：2231-2237.
[12] ZHANG Z, SUN Y, GAO D W, et al.A versatile probability distribution model for wind power forecast errors and its application in economic dispatch[J].IEEE Transactions on Power Systems，2013，28(3) ：3114-3125.
[13] KHOSRAVI Abbas, NAHAVANDI Saeid.Combined nonparametric prediction intervals for wind power generation[J].IEEE Transactions on Sustainable Energy，2013，4(4) ：849-856.
[14] BRI-MATHIAS H, DEBRA L, MICHAEL M.Wind power forecasting error distributions ：an international comparison[C]//Proceedings of the 11th Annual International Workshop on Large-Scale Integration of Wind Power into Power Systems as well as on Transmission Networks for Offshore Wind Power Plants Conference，2012 ：81-90.
[15] 劉燕華，李偉花，劉沖，等. 短期風(fēng)電功率預(yù)測(cè)誤差的混合偏態(tài)分布模型[J] . 中國(guó)電機(jī)工程學(xué)報(bào)，2015，35(10) ：2375-2381.[16] 王彩霞，魯宗相，喬穎，等. 基于非參數(shù)回歸模型的短期風(fēng)電功率預(yù)測(cè)[J] . 電力系統(tǒng)自動(dòng)化，2010，34(16) ：78-82.
[17] 孫建波，吳小珊，張步涵. 基于非參數(shù)核密度估計(jì)的風(fēng)電功率區(qū)間預(yù)測(cè)[J] . 水電能源科學(xué)，2013，31(9) ：233-235.
[18] 周松林，茆美琴，蘇建徽. 風(fēng)電功率短期預(yù)測(cè)及非參數(shù)區(qū)間估計(jì)[J] . 中國(guó)電機(jī)工程學(xué)報(bào)，2011，31(25) ：10-16.
[19] SANCHEZ I.Short-term prediction of wind energy production[J].International Journal of Forecasting，2006，22(1) ：43-56.
[20] 涂嬌嬌，肖白. 風(fēng)電功率波動(dòng)特性分析及其在電力系統(tǒng)中的應(yīng)用[D]. 吉林：東北電力大學(xué)，2015.