本文選題：光伏功率預(yù)測(cè)　切入點(diǎn)：PLS　出處：《東北電力大學(xué)》2017年碩士論文　論文類(lèi)型：學(xué)位論文

【摘要】：光伏發(fā)電是新興的產(chǎn)業(yè)發(fā)電技術(shù),備受青睞。但是由于光伏發(fā)電系統(tǒng)的輸出受到太陽(yáng)輻照強(qiáng)度和天氣因素的影響,使得光伏發(fā)電系統(tǒng)在輸出的時(shí)候有較大的不穩(wěn)定性,事實(shí)上光伏發(fā)電其實(shí)是一種非平穩(wěn)的過(guò)程帶有一定的隨即性。正是這種性質(zhì),會(huì)造成光伏發(fā)電接入電網(wǎng)后對(duì)整個(gè)大電網(wǎng)產(chǎn)生沖擊影響。何時(shí)做出何種電網(wǎng)調(diào)度,是減少?zèng)_擊影響的關(guān)鍵。所以準(zhǔn)確預(yù)測(cè)光伏發(fā)電量,成為許多國(guó)內(nèi)外學(xué)者要研究的問(wèn)題。課題就光伏電站發(fā)電功率短期的預(yù)測(cè)做了深入研究。首先,獲取某光伏電站逆變器上的發(fā)電功率數(shù)據(jù),進(jìn)行數(shù)據(jù)分析,指出天氣類(lèi)型和溫度對(duì)光伏發(fā)電功率有影響。并且,根據(jù)數(shù)據(jù),對(duì)天氣類(lèi)型和溫度做出相關(guān)性分析,得出各自的相關(guān)系數(shù)。天氣類(lèi)型與發(fā)電功率程正相關(guān),且基本處于高度相關(guān)程度。由此使用把天氣類(lèi)型映射為天氣類(lèi)指數(shù)方法。溫度與發(fā)電功率程負(fù)相關(guān),且把最高溫度、最低溫度、平均溫度相關(guān)系數(shù)做對(duì)比,最終確定最高溫度與最低溫度為溫度的影響因素。建立了PLS、RF、SVM、退火優(yōu)化SVM四種預(yù)測(cè)模型。四種模型對(duì)所有的樣本進(jìn)行了預(yù)測(cè)。PLS預(yù)測(cè)模型中,晴天、晴轉(zhuǎn)多云、多云、多云轉(zhuǎn)晴、雨五種天氣類(lèi)型預(yù)測(cè)平均準(zhǔn)確率分別為94.2%、86.3%、81.6%、81.7%、73.6%。RF預(yù)測(cè)模型中,晴天、晴轉(zhuǎn)多云、多云、多云轉(zhuǎn)晴、雨五種天氣類(lèi)型預(yù)測(cè)平均準(zhǔn)確率分別為93.5%、86.1%、82.3%、83.2%、75.3%。SVM預(yù)測(cè)模型中,晴天、晴轉(zhuǎn)多云、多云、多云轉(zhuǎn)晴、雨五種天氣類(lèi)型預(yù)測(cè)平均準(zhǔn)確率分別為94.6%、87.9%、84.3%、85.7%、75.9%。退火優(yōu)化SVM預(yù)測(cè)模型中,晴天、晴轉(zhuǎn)多云、多云、多云轉(zhuǎn)晴、雨五種天氣類(lèi)型預(yù)測(cè)平均準(zhǔn)確率分別為94.8%、90.8%、86.7%、87.4%、79.1%。PLS模型屬于多元回歸模型,其模型結(jié)構(gòu)相對(duì)簡(jiǎn)單,程序操作方便。RF模型、SVM模型、退火優(yōu)化SVM模型具有機(jī)器學(xué)習(xí)能力,無(wú)論哪種天氣類(lèi)型,退火優(yōu)化SVM模型相對(duì)比另外兩種機(jī)器學(xué)習(xí)模型,都有較高的準(zhǔn)確率,SVM模型次之。具有機(jī)器學(xué)習(xí)能力的預(yù)測(cè)模型,在晴轉(zhuǎn)多云、多云、多云轉(zhuǎn)晴等天氣波動(dòng)情況下,有一定的抗干擾能力,但需要一定的程序運(yùn)行時(shí)間。在實(shí)際中,根據(jù)不同需求選擇不同的預(yù)測(cè)模型。
[Abstract]:Photovoltaic power generation is a new industrial power generation technology, which is very popular. However, because the output of photovoltaic power generation system is affected by solar radiation intensity and weather factors, photovoltaic power generation system has greater instability in output. As a matter of fact, photovoltaic power generation is actually a non-stationary process with a certain degree of randomness. It is precisely this kind of property that will cause the impact of photovoltaic power generation on the whole large power grid. When and what kind of grid dispatch will be made. It is the key to reduce the impact of impact. Therefore, accurate prediction of photovoltaic power generation has become a problem to be studied by many scholars at home and abroad. The data of power generation on an inverter of a photovoltaic power plant are obtained, and the data are analyzed, and it is pointed out that the weather type and temperature have an effect on the power of photovoltaic power generation. In addition, according to the data, the correlation between weather type and temperature is analyzed. The correlation coefficient is obtained. The weather type is positively correlated with the generation power process, and is basically in a high degree of correlation. Therefore, the method of mapping weather type to synoptic index is used. The temperature is negatively correlated with the generation power range, and the maximum temperature, The correlation coefficient of minimum temperature and average temperature is compared, and the maximum temperature and the lowest temperature are determined as the influencing factors of temperature. Four prediction models of SVM are established, which are optimized by annealing, and all samples are predicted by four models. The average accuracy of forecasting the five weather types of sunny, sunny to cloudy, cloudy to cloudy, cloudy to sunny, and rain is 94.22 / 86.3s, respectively. The accuracy of forecasting the five weather types is respectively 94.22 / 86.3and 81.6 / 81.6 / 81.7/ 73.6. in the RF forecasting model, sunny, sunny to cloudy, cloudy to cloudy, cloudy to sunny, cloudy to sunny, The average accuracy of forecast for the five types of rain was 93.5, 86.1and 82.3s, respectively. In the prediction model of the five weather types, sunny, sunny to cloudy, cloudy to cloudy, cloudy to sunny, and rain, the average accuracy of forecast of five weather types was 94.60.84.35.70.The average accuracy of SVM model was optimized by annealing, sunny weather, sunny to cloudy, sunny to cloudy, and the average accuracy of forecast was 75.90.In the SVM prediction model, the average accuracy was 94.6% 84.37.70.In the SVM prediction model, the sunny weather, sunny weather, sunny to cloudy, sunny to cloudy, were 94.6%, 87.9% and 85.9%, respectively. The average prediction accuracy of the five weather types of cloudy, cloudy to sunny and rainy is 94.80.88 and 86.77.40.PLS models belong to the multivariate regression model. The model structure is relatively simple, the program operation is convenient, the RF model has the SVM model, and the annealing optimization SVM model has the ability of machine learning. Regardless of weather type, annealing optimized SVM model has higher accuracy than other two machine learning models. In the case of cloudy to sunny weather fluctuation, it has certain anti-interference ability, but it needs certain program running time. In practice, different prediction models are selected according to different demand.
【學(xué)位授予單位】：東北電力大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類(lèi)號(hào)】：TM615

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 劉沛漢;吐?tīng)栠d·伊不拉音;趙力;賈娜;;一種光伏系統(tǒng)短期功率預(yù)測(cè)模型[J];電源技術(shù);2017年02期

2 張玉;萬(wàn)成偉;;基于模糊神經(jīng)網(wǎng)絡(luò)的光伏發(fā)電量短期預(yù)測(cè)[J];電子設(shè)計(jì)工程;2017年02期

3 張程熠;唐雅潔;李永杰;高強(qiáng);江全元;;適用于小樣本的神經(jīng)網(wǎng)絡(luò)光伏預(yù)測(cè)方法[J];電力自動(dòng)化設(shè)備;2017年01期

4 齊紅云;倫淑嫻;;基于模糊雙曲正切模型的短期光伏發(fā)電量預(yù)測(cè)[J];電子設(shè)計(jì)工程;2016年17期

5 宋丹丹;任國(guó)臣;張夢(mèng)松;蘇人奇;;SOFM-LM-BP神經(jīng)網(wǎng)絡(luò)在光伏發(fā)電量預(yù)測(cè)中的應(yīng)用[J];遼寧工業(yè)大學(xué)學(xué)報(bào)(自然科學(xué)版);2016年03期

6 段培永;張潔玨;崔沖;張震;鄒明君;呂東岳;;太陽(yáng)能光伏發(fā)電功率短期智能預(yù)測(cè)方法[J];山東建筑大學(xué)學(xué)報(bào);2016年03期

7 陳瑤琪;;基于典型天氣類(lèi)型計(jì)及隨機(jī)預(yù)測(cè)誤差的光伏發(fā)電短期預(yù)測(cè)研究[J];中國(guó)電力;2016年05期

8 黃敏敏;顏文俊;;基于遺傳算法優(yōu)化神經(jīng)網(wǎng)絡(luò)的光伏發(fā)電預(yù)測(cè)[J];機(jī)電工程;2015年11期

9 高陽(yáng);張碧玲;毛京麗;劉勇;;基于機(jī)器學(xué)習(xí)的自適應(yīng)光伏超短期出力預(yù)測(cè)模型[J];電網(wǎng)技術(shù);2015年02期

10 張華彬;楊明玉;;基于天氣類(lèi)型聚類(lèi)和LS-SVM的光伏出力預(yù)測(cè)[J];電力科學(xué)與工程;2014年10期

相關(guān)碩士學(xué)位論文 前1條

1 趙欣宇;光伏發(fā)電系統(tǒng)功率預(yù)測(cè)的研究與實(shí)現(xiàn)[D];華北電力大學(xué);2012年

，

本文編號(hào)：1615770