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 >> 往年索引

基于VMD-IGWO-SVM的風(fēng)電功率超短期預(yù)測(cè)研究

來(lái)源:電工電氣發(fā)布時(shí)間:2019-01-21 14:21 瀏覽次數(shù):809
基于VMD-IGWO-SVM的風(fēng)電功率超短期預(yù)測(cè)研究
 
沈岳峰,都洪基
(南京理工大學(xué) 自動(dòng)化學(xué)院,江蘇 南京 210094)
 
    摘 要:為了提高風(fēng)電功率預(yù)測(cè)精度,保證風(fēng)能的有效利用,提出一種基于變分模態(tài)分解和改進(jìn)灰狼算法優(yōu)化支持向量機(jī)的風(fēng)電功率超短期組合預(yù)測(cè)模型。采用變分模態(tài)分解將風(fēng)電功率序列分解為一系列具有不同中心頻率的模態(tài)分量以降低其隨機(jī)性,將各分量分別建立支持向量機(jī)預(yù)測(cè)模型,并采用改進(jìn)灰狼算法對(duì)其參數(shù)尋優(yōu),將各分量的預(yù)測(cè)值疊加重構(gòu)得到最終的預(yù)測(cè)值。實(shí)例仿真表明,所提的組合預(yù)測(cè)模型與其他預(yù)測(cè)模型相比具有更高的預(yù)測(cè)精度。
    關(guān)鍵詞:風(fēng)電功率超短期預(yù)測(cè);變分模態(tài)分解;改進(jìn)灰狼算法;支持向量機(jī);預(yù)測(cè)精度
    中圖分類號(hào):TM715     文獻(xiàn)標(biāo)識(shí)碼:A     文章編號(hào):1007-3175(2019)01-0020-06
 
Research on Ultra-Short-Term Wind Power Prediction Based on VMD-IGWO-SVM
 
SHEN Yue-feng, DU Hong-ji
(School of Automation, Nanjing University of Science and Technology, Nanjing 210094, China)
 
    Abstract: In order to improve the accuracy of wind power prediction and to ensure the effective utilization of wind energy, this paper proposed a combined model based on VMD and SVM optimized by IGWO for ultra-short-term wind power prediction. VMD was used to decompose the wind power series into a series of modal components with different central frequencies to reduce its randomness. The SVM prediction model was established for each component and its parameters were optimized by IGWO. The predicted value of each component was superimposed to get the final predicted value.Simulation results show that compared with other prediction models, the proposed combination prediction model has higher prediction accuracy.
    Key words: ultra-short-term wind power prediction; variational mode decomposition; improved grey wolf optimizer; support vector machine; prediction accuracy
 
參考文獻(xiàn)
[1] 董朕,殷豪,孟安波. 基于混合算法優(yōu)化神經(jīng)網(wǎng)絡(luò)的風(fēng)電預(yù)測(cè)模型[J]. 廣東電力,2017,30(2):29-33.
[2] 吳道林. 短期風(fēng)電功率預(yù)測(cè)方法研究[D]. 蕪湖:安徽工程大學(xué),2017.
[3] 譚沛然. 風(fēng)電功率預(yù)測(cè)算法研究[D]. 太原:太原理工大學(xué),2017.
[4] 焦?jié)櫤#K辰雋,林碧英,等. 基于氣象信息因素修正的灰色短期負(fù)荷預(yù)測(cè)模型[J]. 電網(wǎng)技術(shù),2013,37(3):720-725.
[5] 江岳春,張丙江,邢方方,等. 基于混沌時(shí)間序列GA-VNN模型的超短期風(fēng)功率多步預(yù)測(cè)[J]. 電網(wǎng)技術(shù),2015,39(8):2160-2166.
[6] 黎靜華,桑川川,甘一夫,等. 風(fēng)電功率預(yù)測(cè)技術(shù)研究綜述[J]. 現(xiàn)代電力,2017,34(3):1-11.
[7] 赫衛(wèi)國(guó),郝向軍,郭雅娟,等. 基于ARIMA和SVR的光伏電站超短期功率預(yù)測(cè)[J]. 廣東電力,2017,30(8):32-37.
[8] 韓世軍,朱菊,毛吉貴,等. 基于粒子群優(yōu)化支持向量機(jī)的變壓器故障診斷[J]. 電測(cè)與儀表,2014,51(11):71-75.
[9] 陳偉根,滕黎,劉軍, 等. 基于遺傳優(yōu)化支持向量機(jī)的變壓器繞組熱點(diǎn)溫度預(yù)測(cè)模型[J]. 電工技術(shù)學(xué)報(bào),2014,29(1):44-51.
[10] 彭春華,劉剛,孫惠娟. 基于小波分解和微分進(jìn)化支持向量機(jī)的風(fēng)電場(chǎng)風(fēng)速預(yù)測(cè)[J]. 電力自動(dòng)化設(shè)備,2012,32(1):9-13.
[11] 管志威, 陳國(guó)初, 徐余法, 等. 基于改進(jìn)EMD與SVM的風(fēng)電功率短期預(yù)測(cè)模型[J]. 控制工程,2014,21(6):833-837.
[12] DRAGOMIRETSKIY K, ZOSSO D.Variational Mode Decomposition[J]. IEEE Transactions on Signal Processing,2014,62(3):531-544.
[13] BOYD S, PARIKH N, CHU E, et al.Distributed Optimization and Statistical Learning via the Alternating Direction Method of Multipliers[J]. Foundations & Trends in Machine Learning,2011,3(1):1-122.
[14] MIRJALILI S, MIRJALILI S M, LEWIS A. Grey Wolf Optimizer[J]. Advances in Engineering Software, 2014,69(3):46-61.
[15] 呂中亮. 基于變分模態(tài)分解與優(yōu)化多核支持向量機(jī)的旋轉(zhuǎn)機(jī)械早期故障診斷方法研究[D]. 重慶:重慶大學(xué),2016.