發(fā)布時間：2018-03-07 21:46

  本文選題：并網(wǎng)光伏電站　切入點：功率預(yù)測　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】：隨著我國光伏發(fā)電系統(tǒng)得到越來越廣泛的應(yīng)用,隨之而來的問題也越來越多。由于太陽輻照度與季度、晝夜等周期性因素有關(guān),還與陰晴等天氣的非周期因素有關(guān),致使得光伏發(fā)電輸出功率有著隨機性及間歇性等缺陷。當(dāng)前我國儲能技術(shù)還不成熟,當(dāng)大規(guī)模的光伏發(fā)電系統(tǒng)并網(wǎng)時,對電網(wǎng)的電能質(zhì)量及系統(tǒng)穩(wěn)定帶來巨大挑戰(zhàn)。因此對光伏發(fā)電輸出功率進行預(yù)測對于電力系統(tǒng)調(diào)度及電力系統(tǒng)運行的穩(wěn)定性有著舉足輕重的作用。做好光伏發(fā)電功率預(yù)測工作對于擴大光伏產(chǎn)業(yè)規(guī)模及提高光伏產(chǎn)業(yè)發(fā)展速度具有重要意義。 本文在研究光伏發(fā)電特性的基礎(chǔ)上,提出了粒子群優(yōu)化算法(PSO)來優(yōu)化稀疏貝葉斯回歸(SBR)的混合算法,并將其應(yīng)用于光伏功率預(yù)測問題中。通過對光伏發(fā)電特性及影響因素的分析,得出影響出力的主要因素為光照強度、溫度,并以此構(gòu)建樣本集,用上述算法構(gòu)建的模型進行功率預(yù)測。本文采用的稀疏貝葉斯回歸是一種可以解決非線性回歸的有效方法,其參數(shù)的選擇和預(yù)測結(jié)果的精度密切相關(guān)。本文采取的是用粒子群算法來代替?zhèn)鹘y(tǒng)的共軛梯度法以解決稀疏貝葉斯的參數(shù)優(yōu)化過程。經(jīng)過實驗驗證,在未經(jīng)參數(shù)優(yōu)化時,稀疏貝葉斯回歸算法的預(yù)測精度要略高于支持向量機以及神經(jīng)網(wǎng)絡(luò)算法。在參數(shù)優(yōu)化后,預(yù)測精度在原有的基礎(chǔ)上又得到了進一步提高,驗證了算法的有效性。本文在最后本文設(shè)計了一個光伏發(fā)電功率預(yù)測系統(tǒng),給出了系統(tǒng)的各個方面的詳細設(shè)計,包括數(shù)據(jù)庫、系統(tǒng)架構(gòu)、系統(tǒng)功能設(shè)計和一些操作界面。該系統(tǒng)實現(xiàn)了光伏功率預(yù)測的基本功能,包括模型訓(xùn)練、數(shù)據(jù)展示及查詢、預(yù)測結(jié)果展示、誤差比較等,具備一定的實用性。
[Abstract]:With the more and more extensive application of photovoltaic power generation system in China, there are more and more problems. Because solar irradiance is related to periodic factors such as quarterly, day and night, and aperiodic factors such as cloudy and sunny weather, etc. As a result, the output power of photovoltaic power generation has some defects, such as randomness and intermittency. At present, the energy storage technology in China is not mature, when the large-scale photovoltaic power generation system is connected to the grid, Therefore, it is very important to predict the output power of photovoltaic power system for power system dispatching and stability of power system. The work of power prediction is of great significance to expand the scale of photovoltaic industry and improve the speed of development of photovoltaic industry. On the basis of studying the characteristics of photovoltaic power generation, a hybrid algorithm named Particle Swarm Optimization (PSO) is proposed to optimize sparse Bayesian regression (SBR). By analyzing the characteristics of photovoltaic power generation and the influencing factors, the main factors affecting the power are light intensity, temperature, and the sample set is constructed. In this paper, sparse Bayesian regression is an effective method to solve nonlinear regression. The selection of parameters is closely related to the precision of prediction results. In this paper, particle swarm optimization algorithm is used to replace the traditional conjugate gradient method to solve the parameter optimization process of sparse Bayes. The prediction accuracy of sparse Bayesian regression algorithm is slightly higher than that of support vector machine and neural network algorithm. At the end of this paper, a photovoltaic power prediction system is designed, and the detailed design of all aspects of the system, including database, system architecture, is given. The system realizes the basic functions of photovoltaic power prediction, including model training, data display and query, prediction result display, error comparison and so on.
【學(xué)位授予單位】：華北電力大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2014
【分類號】：TM615

【參考文獻】

相關(guān)期刊論文 前9條

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

2 李春來;朱慧敏;景滿德;張杰;;并網(wǎng)型光伏電站功率預(yù)測方法探討[J];電工技術(shù);2010年12期

3 盧靜;翟海青;劉純;王曉蓉;;光伏發(fā)電功率預(yù)測統(tǒng)計方法研究[J];華東電力;2010年04期

4 段其昌;曾勇;黃大偉;段盼;劉頓;;基于擴展記憶粒子群-支持向量回歸的短期電力負荷預(yù)測[J];電力系統(tǒng)保護與控制;2012年02期

5 高鷹,謝勝利;基于模擬退火的粒子群優(yōu)化算法[J];計算機工程與應(yīng)用;2004年01期

6 張相勝;王凱;;高斯過程集成算法的發(fā)酵過程軟測量建模[J];計算機工程與應(yīng)用;2011年33期

7 唐彬;馬穎;崔巖;劉素梅;;基于SVM的光伏最大功率跟蹤的預(yù)測研究[J];西安工業(yè)大學(xué)學(xué)報;2007年04期

8 栗然;李廣敏;;基于支持向量機回歸的光伏發(fā)電出力預(yù)測[J];中國電力;2008年02期

9 張嵐;張艷霞;郭嫦敏;趙杰;;基于神經(jīng)網(wǎng)絡(luò)的光伏系統(tǒng)發(fā)電功率預(yù)測[J];中國電力;2010年09期

，

本文編號：1581090