本文關(guān)鍵詞： 光伏發(fā)電 短期功率預(yù)測(cè) 超短期功率預(yù)測(cè) 相關(guān)系數(shù) 天氣類(lèi)型　出處：《江蘇大學(xué)》2017年碩士論文　論文類(lèi)型：學(xué)位論文

【摘要】：近年來(lái),隨著相關(guān)科技的進(jìn)步,光伏發(fā)電的單位造價(jià)持續(xù)下降,因而得到了快速發(fā)展。太陽(yáng)能作為一種清潔可再生能源,利用太陽(yáng)能進(jìn)行光伏發(fā)電能夠大幅緩解能源危機(jī),減輕由傳統(tǒng)化石燃料帶來(lái)的一系列環(huán)境問(wèn)題。然而,地表太陽(yáng)能屬于間歇性能源,使得光伏電站的發(fā)電功率呈現(xiàn)出波動(dòng)性和間歇性特征。當(dāng)并網(wǎng)光伏電站裝機(jī)容量較大時(shí),電力系統(tǒng)的安全性與穩(wěn)定性將受到影響。因此,需要準(zhǔn)確預(yù)測(cè)光伏電站的發(fā)電功率以配合電力部門(mén)進(jìn)行合理的計(jì)劃和調(diào)度。本文依托兩座并網(wǎng)光伏電站的實(shí)際采集數(shù)據(jù),分析總結(jié)了近年來(lái)國(guó)內(nèi)外相關(guān)領(lǐng)域的研究進(jìn)展,對(duì)光伏電站短期和超短期功率預(yù)測(cè)進(jìn)行了較為詳細(xì)的分析研究,論文主要包括以下幾方面內(nèi)容:(1)根據(jù)相關(guān)理論設(shè)計(jì)了一種地外輻照度計(jì)算器,將獲取到的原始數(shù)據(jù)通過(guò)異常值監(jiān)測(cè)、有效時(shí)間區(qū)間判定、插補(bǔ)缺失數(shù)據(jù)和歸一化等步驟進(jìn)行數(shù)據(jù)預(yù)處理后,建立了用于光伏發(fā)電功率預(yù)測(cè)的數(shù)據(jù)庫(kù);(2)提出了一種基于ELM-SVM的短期功率預(yù)測(cè)模型。首先,根據(jù)天氣預(yù)報(bào)給出的不同天氣類(lèi)型中地外輻照度與發(fā)電功率間的相關(guān)系數(shù),將各天氣類(lèi)型合并成晴天、多云、雨天三種典型天氣類(lèi)型,并分別建立子預(yù)測(cè)模型。之后,利用皮爾遜相關(guān)系數(shù)根據(jù)各典型天氣類(lèi)型的特征,選取針對(duì)性較強(qiáng)的參數(shù)作為子預(yù)測(cè)模型的輸入。最后利用“積分競(jìng)爭(zhēng)制”回歸模型選取法,選取ELM作為晴天條件下的回歸模型,SVM作為多云和雨天條件下的回歸模型。結(jié)果表明ELM-SVM混合預(yù)測(cè)模型能夠發(fā)揮不同回歸模型的優(yōu)勢(shì),相比使用單一模型預(yù)測(cè)方法,該混合預(yù)測(cè)模型具有更強(qiáng)的適應(yīng)能力和更好的預(yù)測(cè)效果;(3)使用歷史發(fā)電功率作為模型輸入,本文提出了基于ELM的超短期功率預(yù)測(cè)模型。相比BP神經(jīng)網(wǎng)絡(luò),ELM具有更好的預(yù)測(cè)效果。最后,根據(jù)ELM模型在不同時(shí)間區(qū)間內(nèi)的誤差分布特征,將歷史發(fā)電功率分時(shí)段訓(xùn)練并建立子預(yù)測(cè)模型,實(shí)驗(yàn)結(jié)果表明,基于ELM的分段式功率預(yù)測(cè)模型在天氣波動(dòng)較大的環(huán)境中表現(xiàn)更佳。
[Abstract]:In recent years, with the progress of related science and technology, the unit cost of photovoltaic power has been continuously reduced, so it has been rapidly developed. Solar energy as a clean and renewable energy. Solar photovoltaic power generation can significantly alleviate the energy crisis and alleviate a series of environmental problems caused by traditional fossil fuels. However, surface solar energy is an intermittent energy source. When the installed capacity of grid-connected photovoltaic power station is large, the security and stability of power system will be affected. It is necessary to accurately predict the generation power of photovoltaic power station in order to cooperate with the power department to plan and dispatch reasonably. This paper relies on the actual acquisition data of two grid-connected photovoltaic power stations. This paper analyzes and summarizes the research progress in the related fields at home and abroad in recent years, and makes a more detailed analysis and research on the short-term and ultra-short-term power prediction of photovoltaic power plants. This paper mainly includes the following aspects: 1) according to the relevant theory, a kind of extraterrestrial irradiance calculator is designed. The original data is monitored by outliers and the effective time interval is determined. After preprocessing the missing data and normalized data, the database of photovoltaic power prediction is established. In this paper, a short-term power prediction model based on ELM-SVM is proposed. Firstly, the correlation coefficient between external irradiance and generation power in different weather types is given. The weather types are combined into three typical weather types: sunny, cloudy and rainy, and sub-prediction models are established respectively. After that, Pearson correlation coefficient is used according to the characteristics of each typical weather type. The parameters are selected as the input of the sub-prediction model. Finally, the "integral competition system" regression model selection method is used to select ELM as the regression model under sunny conditions. SVM is a regression model under cloudy and rainy conditions. The results show that the ELM-SVM hybrid prediction model can play the advantages of different regression models, compared with the single model prediction method. The hybrid prediction model has stronger adaptability and better prediction effect. Using the historical generation power as the input of the model, this paper presents an ultra-short-term power prediction model based on ELM. It has better prediction effect than BP neural network. Finally. According to the error distribution characteristics of the ELM model in different time intervals, the historical generation power is trained in different periods and the sub-prediction model is established. The experimental results show that. The segmented power prediction model based on ELM performs better in the fluctuating weather environment.
【學(xué)位授予單位】：江蘇大學(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9條

1 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(cè)模型[J];中國(guó)電機(jī)工程學(xué)報(bào);2015年03期

2 袁曉玲;施俊華;徐杰彥;;計(jì)及天氣類(lèi)型指數(shù)的光伏發(fā)電短期出力預(yù)測(cè)[J];中國(guó)電機(jī)工程學(xué)報(bào);2013年34期

3 王飛;米增強(qiáng);甄釗;楊光;周海明;;基于天氣狀態(tài)模式識(shí)別的光伏電站發(fā)電功率分類(lèi)預(yù)測(cè)方法[J];中國(guó)電機(jī)工程學(xué)報(bào);2013年34期

4 郭旭陽(yáng);謝開(kāi)貴;胡博;陳濤;龍虹毓;;計(jì)入光伏發(fā)電的電力系統(tǒng)分時(shí)段隨機(jī)生產(chǎn)模擬[J];電網(wǎng)技術(shù);2013年06期

5 代倩;段善旭;蔡濤;陳昌松;陳正洪;邱純;;基于天氣類(lèi)型聚類(lèi)識(shí)別的光伏系統(tǒng)短期無(wú)輻照度發(fā)電預(yù)測(cè)模型研究[J];中國(guó)電機(jī)工程學(xué)報(bào);2011年34期

6 張艷霞;趙杰;;基于反饋型神經(jīng)網(wǎng)絡(luò)的光伏系統(tǒng)發(fā)電功率預(yù)測(cè)[J];電力系統(tǒng)保護(hù)與控制;2011年15期

7 李冬輝;王鶴雄;朱曉丹;李征;;光伏并網(wǎng)發(fā)電系統(tǒng)幾個(gè)關(guān)鍵問(wèn)題的研究[J];電力系統(tǒng)保護(hù)與控制;2010年21期

8 陳昌松;段善旭;殷進(jìn)軍;;基于神經(jīng)網(wǎng)絡(luò)的光伏陣列發(fā)電預(yù)測(cè)模型的設(shè)計(jì)[J];電工技術(shù)學(xué)報(bào);2009年09期

9 王炳忠;太陽(yáng)輻射計(jì)算 講座 第三講地外水平面輻射量的計(jì)算[J];太陽(yáng)能;1999年04期

，

本文編號(hào)：1442745