發(fā)布時(shí)間：2018-05-31 12:57

  本文選題：光伏功率預(yù)測 + 灰色關(guān)聯(lián)分析　； 參考：《東北電力大學(xué)》2017年碩士論文

【摘要】：太陽能發(fā)電受到日照,季節(jié)變化及天氣波動等氣候條件的影響,使得發(fā)電系統(tǒng)的輸出功率具有間斷性、周期性和不確定性的特點(diǎn)。光伏發(fā)電功率預(yù)測技術(shù)作為光伏電站建站必備的技術(shù)條件,關(guān)系到電站并網(wǎng)及電網(wǎng)調(diào)度的準(zhǔn)確性和合理性,若能準(zhǔn)確掌握短期內(nèi)光伏電站的輸出功率,可大大降低電站并網(wǎng)風(fēng)險(xiǎn),提高電網(wǎng)運(yùn)行的安全性和穩(wěn)定性。本文在對氣象因素如何影響光伏發(fā)電功率輸出以及功率預(yù)測技術(shù)基礎(chǔ)進(jìn)行了簡要介紹之后,將光伏發(fā)電功率短期預(yù)測問題分為超短期和短期兩部分。針對超短期輸出功率的預(yù)測,提出一種基于氣象因素的相似日選取方法:利用光伏發(fā)電系統(tǒng)的歷史氣象信息建立氣象特征向量,通過計(jì)算灰色關(guān)聯(lián)度尋找到預(yù)測日的相似歷史日。然后使用相似日歷史數(shù)據(jù)和小波神經(jīng)網(wǎng)絡(luò)(WNN,Wavelet Neural Network)構(gòu)建一種光伏發(fā)電功率的超短期預(yù)測模型,通過使用某光伏發(fā)電系統(tǒng)的歷史數(shù)據(jù)進(jìn)行建模,對所選兩類不同天氣類型的預(yù)測日的出力情況進(jìn)行逐時(shí)刻預(yù)測,預(yù)測結(jié)果顯示模型預(yù)測效果較好,尤其對于理想晴天條件下預(yù)測的更加精確。針對短期輸出功率的預(yù)測,提出一種基于思維進(jìn)化算法(MEA,Mind Evolutionary Algorithm)優(yōu)化BP神經(jīng)網(wǎng)絡(luò)的光伏功率短期預(yù)測模型,通過我國青海省錫鐵山裝機(jī)量100MW的光伏電站為期一年的歷史運(yùn)行數(shù)據(jù)進(jìn)行建模,按照季節(jié)劃分為四個(gè)預(yù)測單元分別對預(yù)測模型進(jìn)行訓(xùn)練和電站出力預(yù)測,通過與電站的實(shí)際出力情況和電站所配備的預(yù)測系統(tǒng)短期預(yù)測值的比較分析,由BP算法和MEA-BP算法所構(gòu)建的模型均達(dá)到了一定的預(yù)測精度,其中MEA-BP模型有效的降低了BP網(wǎng)絡(luò)模型的預(yù)測誤差。最后將相似日與神經(jīng)網(wǎng)絡(luò)結(jié)合,建立一個(gè)基于相似日和神經(jīng)網(wǎng)絡(luò)的光伏功率短期預(yù)測模型:通過設(shè)置兩組對照實(shí)驗(yàn):一組使用相似歷史日的數(shù)據(jù)來訓(xùn)練網(wǎng)絡(luò)并進(jìn)行預(yù)測(實(shí)驗(yàn)組),一組使用相鄰歷史日數(shù)據(jù)來訓(xùn)練網(wǎng)絡(luò)并進(jìn)行預(yù)測(對照組),對比實(shí)驗(yàn)的結(jié)果顯示實(shí)驗(yàn)組的預(yù)測效果更為準(zhǔn)確。經(jīng)過反復(fù)預(yù)測實(shí)驗(yàn),驗(yàn)證了課題所提出的預(yù)測模型能夠?qū)τ行У念A(yù)測光伏發(fā)電系統(tǒng)的輸出功率,預(yù)測結(jié)果也表明基于神經(jīng)網(wǎng)絡(luò)的預(yù)測模型在一定程度上能夠滿足實(shí)際應(yīng)用需求,在光伏電站建站時(shí)對功率預(yù)測技術(shù)的設(shè)計(jì)具有一定的參考價(jià)值。
[Abstract]:Solar power generation is affected by the weather conditions such as sunshine, seasonal variation and weather fluctuation, which makes the output power of the power generation system have the characteristics of discontinuity, periodicity and uncertainty. As a necessary technical condition for the construction of photovoltaic power station, PV generation power prediction technology is related to the accuracy and rationality of grid connection and grid dispatching. If the output power of photovoltaic power station can be accurately grasped in the short term, It can greatly reduce the risk of grid connection and improve the security and stability of power grid operation. After a brief introduction of how meteorological factors affect the output of photovoltaic power generation and the technical basis of power prediction, the short-term prediction of photovoltaic power generation is divided into two parts: ultra short term and short term. According to the prediction of ultra-short-term output power, a similar day selection method based on meteorological factors is proposed: the meteorological characteristic vector is established by using the historical meteorological information of photovoltaic power generation system. The similar historical days of the predicted days are found by calculating the grey correlation degree. Then, using the similar daily historical data and wavelet neural network (WNNN) to construct an ultra-short-term prediction model of photovoltaic power generation, using the historical data of a photovoltaic power generation system to model. The prediction results show that the forecasting effect of the model is better, especially for the ideal sunny weather conditions. In order to predict the short-term output power, a short-term PV power prediction model based on the thinking evolutionary algorithm (MEA ind Evolutionary algorithm) is proposed to optimize the BP neural network. Based on the historical operation data of 100MW photovoltaic power station in Xitieshan of Qinghai Province for one year, the forecasting model is divided into four forecasting units according to the seasons, and the forecasting model is trained and the power generation of the power station is predicted. By comparing with the actual force of the power station and the short-term prediction value of the forecasting system equipped with the power station, the model constructed by BP algorithm and MEA-BP algorithm has achieved a certain prediction accuracy. MEA-BP model can effectively reduce the prediction error of BP network model. Finally, the similar days are combined with neural networks. Establish a short-term photovoltaic power prediction model based on similar days and neural networks: train and predict the network by setting up two groups of controlled experiments: one group uses data from similar historical days to train the network and make prediction (experimental group, group using adjacent data) Historical daily data to train the network and predict (control group, the results of comparative experiments show that the experimental group is more accurate prediction results. After repeated prediction experiments, it is verified that the proposed prediction model can effectively predict the output power of photovoltaic power generation system. The prediction results also show that the prediction model based on neural network can meet the practical application needs to a certain extent. It has certain reference value for the design of power prediction technology in the construction of photovoltaic power station.
【學(xué)位授予單位】：東北電力大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2017
【分類號】：TP183;TM615

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 丁明;鮑玉瑩;畢銳;;應(yīng)用改進(jìn)馬爾科夫鏈的光伏出力時(shí)間序列模擬[J];電網(wǎng)技術(shù);2016年02期

2 高沖;王凱;;基于微源控制-小波神經(jīng)網(wǎng)絡(luò)的微網(wǎng)功率預(yù)測[J];電測與儀表;2015年18期

3 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[J];電測與儀表;2015年11期

4 錢振;蔡世波;顧宇慶;童建軍;鮑官軍;;光伏發(fā)電功率預(yù)測方法研究綜述[J];機(jī)電工程;2015年05期

5 朱想;居蓉蓉;程序;丁宇宇;周海;;組合數(shù)值天氣預(yù)報(bào)與地基云圖的光伏超短期功率預(yù)測模型[J];電力系統(tǒng)自動化;2015年06期

6 肖俊明;韋學(xué)輝;李燕斌;;基于BP神經(jīng)網(wǎng)絡(luò)和遺傳算法的光伏功率預(yù)測的研究[J];計(jì)算機(jī)測量與控制;2015年02期

7 黨耀國;王俊杰;康文芳;;灰色預(yù)測技術(shù)研究進(jìn)展綜述[J];上海電機(jī)學(xué)院學(xué)報(bào);2015年01期

8 陳志寶;丁杰;周海;程序;朱想;;地基云圖結(jié)合徑向基函數(shù)人工神經(jīng)網(wǎng)絡(luò)的光伏功率超短期預(yù)測模型[J];中國電機(jī)工程學(xué)報(bào);2015年03期

9 王倩;張智晟;王帥;曹東亮;;基于PSO-RNN的光伏發(fā)電功率預(yù)測研究[J];青島大學(xué)學(xué)報(bào)(工程技術(shù)版);2014年04期

10 羅建春;晁勤;羅洪;冉鴻;楊杰;羅慶;阿里努爾·阿木提;;基于LVQ-GA-BP神經(jīng)網(wǎng)絡(luò)光伏電站出力短期預(yù)測[J];電力系統(tǒng)保護(hù)與控制;2014年13期

相關(guān)碩士學(xué)位論文 前1條

1 王坤;考慮多重不確定性因素的光伏出力預(yù)測研究[D];華北電力大學(xué);2013年

，

本文編號：1959754