發(fā)布時(shí)間：2018-02-01 03:31

  本文關(guān)鍵詞： 風(fēng)力發(fā)電 風(fēng)速預(yù)測(cè) 時(shí)間序列 Elman神經(jīng)網(wǎng)絡(luò) BP神經(jīng)網(wǎng)絡(luò) 組合模型　出處：《華北電力大學(xué)》2014年碩士論文　論文類型：學(xué)位論文

【摘要】：風(fēng)能以其可再生、無(wú)污染的特性越來(lái)越受到人們的關(guān)注。但由于風(fēng)速的波動(dòng)性和隨機(jī)性,風(fēng)機(jī)出力很不穩(wěn)定。隨著風(fēng)力發(fā)電在電網(wǎng)中所占的比重逐漸增加,其對(duì)電力系統(tǒng)的安全穩(wěn)定運(yùn)行一定會(huì)造成一些不利影響。風(fēng)電并網(wǎng)及電力調(diào)度中,風(fēng)速預(yù)測(cè)的準(zhǔn)確性可以提供非常重要的參考,大大的消除風(fēng)速波動(dòng)對(duì)電網(wǎng)的影響。鑒于這些原因,對(duì)風(fēng)電場(chǎng)風(fēng)速進(jìn)行預(yù)測(cè)研究是非常有意義的。 本文針對(duì)風(fēng)速數(shù)據(jù)的非線性特性,利用改進(jìn)的Elman神經(jīng)網(wǎng)絡(luò)修正ARIMA模型預(yù)測(cè)結(jié)果的方法,運(yùn)用時(shí)間序列與神經(jīng)網(wǎng)絡(luò)的組合模型對(duì)短期風(fēng)速預(yù)測(cè)進(jìn)行研究。先利用ARIMA模型對(duì)風(fēng)速進(jìn)行預(yù)測(cè),其線性規(guī)律信息包含在時(shí)間序列預(yù)測(cè)結(jié)果中,非線性規(guī)律包含在預(yù)測(cè)誤差中。再將ARIMA模型的預(yù)測(cè)誤差及歷史風(fēng)速一階差分序列作為改進(jìn)的Elman神經(jīng)網(wǎng)絡(luò)輸入變量,將ARIMA模型的風(fēng)速預(yù)測(cè)誤差作為輸出變量。最后將ARIMA模型預(yù)測(cè)結(jié)果與Elman神經(jīng)網(wǎng)絡(luò)的誤差預(yù)測(cè)結(jié)果疊加,得到最終修正后的預(yù)測(cè)風(fēng)速。 為證明方法的有效性,分別與單一ARIMA模型、ARIMA-BP神經(jīng)網(wǎng)絡(luò)組合模型進(jìn)行對(duì)比,對(duì)實(shí)際歷史風(fēng)速數(shù)據(jù)進(jìn)行仿真預(yù)測(cè)。經(jīng)驗(yàn)證,利用改進(jìn)Elman神經(jīng)網(wǎng)絡(luò)修正ARIMA模型預(yù)測(cè)誤差,比單一ARIMA模型能夠更好的減小預(yù)測(cè)滯后性,提高預(yù)測(cè)精度、減小預(yù)測(cè)誤差；比ARIMA-BP神經(jīng)網(wǎng)絡(luò)組合模型訓(xùn)練速度提高了30%以上。 通過(guò)以上對(duì)風(fēng)速預(yù)測(cè)問(wèn)題的研究,運(yùn)用組合模型進(jìn)行了較為深入的探討,并進(jìn)行了數(shù)據(jù)處理及仿真,可以發(fā)現(xiàn)ARIMA-Elman神經(jīng)網(wǎng)絡(luò)組合模型比單一模型有更大的優(yōu)越性,為解決實(shí)際工程問(wèn)題提供了一定的參考。
[Abstract]:Wind energy has attracted more and more attention due to its renewable and pollution-free characteristics. However, due to the volatility and randomness of wind speed, the wind power output is very unstable. With the increasing proportion of wind power generation in power grid, wind power generation is becoming more and more important. It will inevitably cause some adverse effects on the safe and stable operation of power system. The accuracy of wind speed prediction can provide a very important reference in wind power grid connection and power dispatching. The influence of wind speed fluctuation on power grid is greatly eliminated. For these reasons, it is very meaningful to predict the wind speed of wind farm. According to the nonlinear characteristics of wind speed data, the improved Elman neural network is used to modify the prediction results of ARIMA model. Using the combined model of time series and neural network, the short-term wind speed prediction is studied. First, the ARIMA model is used to predict the wind speed, and the linear law information is included in the prediction results of time series. The nonlinear law is included in the prediction error, and then the prediction error of ARIMA model and the first order difference sequence of historical wind speed are taken as the input variables of the improved Elman neural network. The wind speed prediction error of ARIMA model is taken as the output variable. Finally, the prediction result of ARIMA model is superposed with the error prediction result of Elman neural network, and the final modified predicted wind speed is obtained. In order to prove the effectiveness of the method, the actual historical wind speed data are simulated and forecasted by comparing with the single ARIMA model ARIMA-BP neural network combination model. The improved Elman neural network is used to correct the prediction error of ARIMA model, which can reduce the prediction lag, improve the prediction accuracy and reduce the prediction error better than the single ARIMA model. The training speed of the combined model is more than 30% higher than that of the ARIMA-BP neural network. Through the above research on wind speed prediction, the combined model is used to conduct a more in-depth discussion, and the data processing and simulation are carried out. It can be found that the combined model of ARIMA-Elman neural network has more advantages than the single model, which provides a certain reference for solving practical engineering problems.
【學(xué)位授予單位】：華北電力大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2014
【分類號(hào)】：TM614

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 儲(chǔ)茂得;周松林;;基于小波分析與神經(jīng)網(wǎng)絡(luò)的風(fēng)電場(chǎng)短期風(fēng)速預(yù)測(cè)[J];安徽科技學(xué)院學(xué)報(bào);2011年01期

2 尹彰,周宗仁;A Study of Wind Statistics Through Auto-Regressive and Moving-Average (ARMA) Modeling[J];China Ocean Engineering;2001年01期

3 戴浪;黃守道;黃科元;葉盛;;風(fēng)電場(chǎng)風(fēng)速的神經(jīng)網(wǎng)絡(luò)組合預(yù)測(cè)模型[J];電力系統(tǒng)及其自動(dòng)化學(xué)報(bào);2011年04期

4 楊錫運(yùn);孫翰墨;;基于時(shí)間序列模型的風(fēng)電場(chǎng)風(fēng)速預(yù)測(cè)研究[J];動(dòng)力工程學(xué)報(bào);2011年03期

5 楊秀媛,梁貴書;風(fēng)力發(fā)電的發(fā)展及其市場(chǎng)前景[J];電網(wǎng)技術(shù);2003年07期

6 董安正,趙國(guó)藩;人工神經(jīng)網(wǎng)絡(luò)在短期資料風(fēng)速估計(jì)方面的應(yīng)用[J];工程力學(xué);2003年05期

7 常太華;王璐;馬巍;;基于AR、ARIMA模型的風(fēng)速預(yù)測(cè)[J];華東電力;2010年01期

8 楊剛;陳鳴;;基于BP神經(jīng)網(wǎng)絡(luò)的風(fēng)速預(yù)測(cè)和風(fēng)能發(fā)電潛力分析[J];華東電力;2010年02期

9 王宏偉;楊先一;金文標(biāo);;基于Elman網(wǎng)絡(luò)的時(shí)延預(yù)測(cè)及其改進(jìn)[J];計(jì)算機(jī)工程與應(yīng)用;2008年06期

10 康重慶,夏清,相年德;灰色系統(tǒng)參數(shù)估計(jì)與不良數(shù)據(jù)辨識(shí)[J];清華大學(xué)學(xué)報(bào)(自然科學(xué)版);1997年04期

相關(guān)博士學(xué)位論文 前1條

1 紀(jì)國(guó)瑞;風(fēng)電場(chǎng)風(fēng)速軟測(cè)量與預(yù)測(cè)及短期風(fēng)速數(shù)值模擬方法研究[D];華北電力大學(xué)（北京）;2009年

，

本文編號(hào)：1480814