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

基于PSO-ICA-BP神經(jīng)網(wǎng)絡(luò)的短期風(fēng)電功率預(yù)測(cè)

來(lái)源:電工電氣發(fā)布時(shí)間:2019-02-19 12:19 瀏覽次數(shù):802
基于PSO-ICA-BP神經(jīng)網(wǎng)絡(luò)的短期風(fēng)電功率預(yù)測(cè)
 
王帥哲1,王金梅1,2,王永奇1,馬文濤1
(1 寧夏大學(xué) 物理與電子電氣工程學(xué)院,寧夏 銀川 750021;
2 寧夏沙漠信息智能感知自治區(qū)重點(diǎn)實(shí)驗(yàn)室,寧夏 銀川 750021)
 
    摘 要:針對(duì)傳統(tǒng)的BP神經(jīng)網(wǎng)絡(luò)對(duì)短期風(fēng)電功率預(yù)測(cè)精度不高的缺點(diǎn),提出粒子群算法改進(jìn)帝國(guó)競(jìng)爭(zhēng)算法(PSO-ICA),通過(guò)PSO算法改進(jìn)殖民地同化操作提高ICA 算法的全局尋優(yōu)能力,輸出全局最優(yōu)解作為BP神經(jīng)網(wǎng)絡(luò)初始權(quán)值閾值。同時(shí)用主成分分析法降維壓縮輸入數(shù)據(jù),提高網(wǎng)絡(luò)泛化能力。利用PSOICA-BP預(yù)測(cè)模型對(duì)某風(fēng)電場(chǎng)實(shí)際風(fēng)電功率數(shù)據(jù)進(jìn)行預(yù)測(cè),仿真結(jié)果表明該模型預(yù)測(cè)誤差更小,對(duì)短期風(fēng)電功率預(yù)測(cè)更有效。
    關(guān)鍵詞:帝國(guó)競(jìng)爭(zhēng)算法;粒子群算法;BP神經(jīng)網(wǎng)絡(luò);風(fēng)電功率預(yù)測(cè)
    中圖分類號(hào):TM614;TM715     文獻(xiàn)標(biāo)識(shí)碼:A     文章編號(hào):1007-3175(2019)02-0007-05
 
Short-Term Wind Power Forecast Based on PSO-ICA-BP Neural Network
 
WANG Shuai-zhe1, WANG Jin-mei1,2, WANG Yong-qi1, MA Wen-tao1
(1 School of Physics and Electronic-Electrical Engineering, Ningxia University, Yinchuan 750021, China;
2 Key Laboratory of Ningxia Desert Information Intelligent Perception Autonomous Region, Yinchuan 750021, China)
 
    Abstract: In view of the shortcomings of the traditional BP neural network for short-term wind power prediction, the particle swarm optimization algorithm (PSO) was proposed to improve the Empire competition algorithm (PSO-ICA), to improve the diversity of colonial assimilation, and to optimize the initial weight threshold of the BP neural network by the output of the global optimal solution. The principal component analysis method was used to reduce dimension and to compress input data and improved the network generalization ability. The PSO-ICA-BP prediction model was used to predict the actual wind power data of certain wind farm. The simulation results show that the prediction error of this PSO-ICA-BP model is smaller and more effective for the short-term wind power prediction.
    Key words: imperial competition algorithm; particle swarm optimization; BP neural network; wind power forcast
 
參考文獻(xiàn)
[1] 王焱,汪震,黃民翔,等. 基于OS-ELM和Bootstrap方法的超短期風(fēng)電功率預(yù)測(cè)[J]. 電力系統(tǒng)自動(dòng)化,2014,38(6):14-19.
[2] 張彥恒,鄭玉玉. 基于RBF神經(jīng)網(wǎng)絡(luò)的風(fēng)電場(chǎng)功率預(yù)測(cè)研究[J]. 南方農(nóng)機(jī),2018,49(7):192.
[3] 田淑慧,于惠鈞,趙巧紅,等. 基于經(jīng)驗(yàn)?zāi)B(tài)分解的PSO-SVM風(fēng)電功率短期預(yù)測(cè)[J]. 湖南工業(yè)大學(xué)學(xué)報(bào),2018,32(3):59-64.
[4] 周松林,茆美琴,蘇建徽. 基于主成分分析與人工神經(jīng)網(wǎng)絡(luò)的風(fēng)電功率預(yù)測(cè)[J]. 電網(wǎng)技術(shù),2011,35(9):128-132.
[5] 王強(qiáng),汪姚,胡紅颯,等. 基于BP神經(jīng)網(wǎng)絡(luò)算法的風(fēng)電功率預(yù)測(cè)[J]. 科技和產(chǎn)業(yè),2014,14(4):143-146.
[6] 劉帥, 劉長(zhǎng)良. 基于帝國(guó)競(jìng)爭(zhēng)算法的主汽溫控制系統(tǒng)參數(shù)優(yōu)化研究[J]. 系統(tǒng)仿真學(xué)報(bào),2017,29(2):368-373.
[7] 楊曉博, 李陽(yáng), 肖朝霞, 等. 改進(jìn)粒子群算法的自動(dòng)阻抗匹配技術(shù)[J]. 重慶大學(xué)學(xué)報(bào),2016,39(6):41-48.
[8] 朱曉青,馬定寰,李圣清,等. 基于BP神經(jīng)網(wǎng)絡(luò)的微電網(wǎng)蓄電池荷電狀態(tài)估計(jì)[J]. 電子測(cè)量與儀器學(xué)報(bào),2017,31(12):2042-2048.
[9] 馬廣慧,馬豆豆,邵秀麗. 基于遺傳BP神經(jīng)網(wǎng)絡(luò)的三七價(jià)格預(yù)測(cè)[J]. 天津師范大學(xué)學(xué)報(bào)( 自然科學(xué)版),2017,7(6):76-80.
[10] LI Dong jie, LI Yang yang, LI Jun xiang, et al. Gesture Recognition Based on BP Neural Network Improved by Chaotic Genetic Algorithm[J]. International Journal of Automation and Computing,2018,15(3):267-276.
[11] 張曉東,楊圣祥. 基于PCA與NARX的市政工程造價(jià)組合預(yù)測(cè)[J]. 控制工程,2017,24(12):2485-2490.
[12] 李亞,蔣偉,樊汝森,等. 基于BP神經(jīng)網(wǎng)絡(luò)的智能臺(tái)區(qū)識(shí)別方法研究[J]. 電測(cè)與儀表,2017,54(3):25-30.
[13] 張立影,孟令甲,王澤忠. 基于雙層BP神經(jīng)網(wǎng)絡(luò)的光伏電站輸出功率預(yù)測(cè)[J]. 電測(cè)與儀表,2015,52(11):31-35.