【摘要】：隨著對(duì)電能需求的增加，電力系統(tǒng)的發(fā)展及改進(jìn)變得更加重要。電力系統(tǒng)的負(fù)荷預(yù)測(cè)對(duì)系統(tǒng)調(diào)度的自動(dòng)化十分重要，并且對(duì)于電力系統(tǒng)的安全穩(wěn)定及經(jīng)濟(jì)運(yùn)行具有重要意義。負(fù)荷預(yù)測(cè)的精度直接影響著電網(wǎng)的安全穩(wěn)定，其預(yù)測(cè)結(jié)果為發(fā)電機(jī)組的運(yùn)行提供幫助，為電廠的燃料供應(yīng)計(jì)劃提供依據(jù)，同時(shí)能夠提高對(duì)系統(tǒng)的控制。預(yù)測(cè)結(jié)果不準(zhǔn)確或誤差過(guò)大會(huì)影響發(fā)電部門(mén)的燃料合理配置，減少其收益。研究具有精度高且實(shí)用性強(qiáng)的負(fù)荷預(yù)測(cè)方法對(duì)于電力的市場(chǎng)化及智能電網(wǎng)的發(fā)展是非常必要的。 本文通過(guò)查閱相關(guān)文獻(xiàn)，介紹了電力系統(tǒng)負(fù)荷預(yù)測(cè)的研究現(xiàn)狀，分析并比較現(xiàn)有的不同預(yù)測(cè)方法的特點(diǎn)，具體研究人工神經(jīng)網(wǎng)絡(luò)方法的原理及學(xué)習(xí)算法，它通過(guò)對(duì)人腦基本特性抽象和模擬，形成一種自適應(yīng)的并行信息處理方法，具有自學(xué)習(xí)和非線性映射等特點(diǎn)，對(duì)于電力系統(tǒng)的負(fù)荷預(yù)測(cè)有重要的應(yīng)用價(jià)值。文中詳細(xì)介紹了誤差反向傳播（Back Propagation，BP）神經(jīng)網(wǎng)絡(luò)和徑向基函數(shù)（Radial Basis Function，RBF）神經(jīng)網(wǎng)絡(luò)的模型結(jié)構(gòu)及其學(xué)習(xí)算法，分別建立了基于BP神經(jīng)網(wǎng)絡(luò)和RBF神經(jīng)網(wǎng)絡(luò)的電力負(fù)荷預(yù)測(cè)模型。建立模型的過(guò)程，對(duì)輸入的原始數(shù)據(jù)進(jìn)行預(yù)處理，去除不良數(shù)據(jù)并補(bǔ)充缺失數(shù)據(jù)；為避免神經(jīng)元飽和，對(duì)輸入樣本作歸一化處理；對(duì)于模型的初始權(quán)值及學(xué)習(xí)參數(shù)的選取也進(jìn)行了分析。對(duì)建立的兩個(gè)模型進(jìn)行比較，BP神經(jīng)網(wǎng)絡(luò)模型的所需的學(xué)習(xí)訓(xùn)練時(shí)間較長(zhǎng)，收斂性差，容易陷入局部極小情況；RBF神經(jīng)網(wǎng)絡(luò)模型的訓(xùn)練速度較快，收斂性好，，對(duì)于電力系統(tǒng)的負(fù)荷預(yù)測(cè)具有更大的優(yōu)勢(shì)。然后介紹了模糊控制理論，模糊理論控制方法不必建立精確的數(shù)學(xué)模型，便可以實(shí)現(xiàn)對(duì)復(fù)雜系統(tǒng)的控制。具體介紹模糊控制器的結(jié)構(gòu)及其設(shè)計(jì)過(guò)程，包括輸入變量選取及模糊推理和判決。利用模糊控制理論對(duì)RBF神經(jīng)網(wǎng)絡(luò)模型進(jìn)行調(diào)整改進(jìn)，提高其收斂速度，減少訓(xùn)練的時(shí)間，建立基于RBF神經(jīng)網(wǎng)絡(luò)與模糊控制相結(jié)合的電力系統(tǒng)負(fù)荷預(yù)測(cè)模型。 利用建立的BP神經(jīng)網(wǎng)絡(luò)、RBF神經(jīng)網(wǎng)絡(luò)模型及RBF神經(jīng)網(wǎng)絡(luò)與模糊控制結(jié)合的模型，對(duì)某地區(qū)的實(shí)際負(fù)荷進(jìn)行了預(yù)測(cè)，并對(duì)結(jié)果進(jìn)行了誤差分析與比較。這幾種方法所得的預(yù)測(cè)結(jié)果的精度都能夠滿足電力部門(mén)的實(shí)際要求，說(shuō)明了他們的有效性及實(shí)用性。應(yīng)用RBF神經(jīng)網(wǎng)絡(luò)與模糊控制相結(jié)合的模型所得的結(jié)果誤差最小，預(yù)測(cè)效果更好，說(shuō)明該方法對(duì)于電力系統(tǒng)的負(fù)荷預(yù)測(cè)具有實(shí)用意義。
[Abstract]:With the increase of power demand, the development and improvement of power system becomes more and more important. The load forecasting of power system is very important to the automation of power system dispatching, and it is of great significance to the safety, stability and economic operation of power system. The accuracy of load forecasting directly affects the safety and stability of power grid. The forecasting results provide help for the operation of generating units, provide the basis for the fuel supply plan of power plants, and improve the control of the system at the same time. Inaccurate prediction results or errors affect the rational allocation of fuel in the power generation sector and reduce its benefits. It is necessary to study load forecasting methods with high accuracy and practicability for the development of power market and smart grid. In this paper, the current situation of load forecasting in power system is introduced, the characteristics of different forecasting methods are analyzed and compared, and the principle and learning algorithm of artificial neural network are studied in detail. By abstracting and simulating the basic characteristics of human brain, it forms an adaptive parallel information processing method, which has the characteristics of self-learning and nonlinear mapping, and has important application value for power system load forecasting. In this paper, the model structure and learning algorithm of error back propagation (Back Propagation,BP) neural network and radial basis function (Radial Basis Function,RBF) neural network are introduced in detail. Power load forecasting models based on BP neural network and RBF neural network are established respectively. In order to avoid neuronal saturation, the input sample is normalized by pre-processing the input original data, removing the bad data and supplementing the missing data. The selection of initial weights and learning parameters is also analyzed. Compared with the two models, the BP neural network model needs long learning and training time, poor convergence, easy to fall into the local minimum; The training speed of RBF neural network model is fast and the convergence is good. It has more advantages for power system load forecasting. Then the fuzzy control theory is introduced. The fuzzy theory control method does not need to establish the accurate mathematical model to realize the control of the complex system. The structure and design process of fuzzy controller are introduced in detail, including input variable selection, fuzzy reasoning and decision. The fuzzy control theory is used to adjust and improve the RBF neural network model to improve its convergence speed and reduce the training time. A power system load forecasting model based on the combination of RBF neural network and fuzzy control is established. Using the established BP neural network, RBF neural network model and RBF neural network combined with fuzzy control model, the actual load in a certain area is forecasted, and the error analysis and comparison of the results are made. The accuracy of the prediction results obtained by these methods can meet the practical requirements of the power sector, which shows their effectiveness and practicability. The model based on RBF neural network and fuzzy control has the smallest error and better prediction effect. It shows that this method is of practical significance for power system load forecasting.
【學(xué)位授予單位】：沈陽(yáng)工業(yè)大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2014
【分類(lèi)號(hào)】：TM715;TP183

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 鞠平,姜巍,趙夏陽(yáng),王俊鍇,張世學(xué),劉琰;96點(diǎn)短期負(fù)荷預(yù)測(cè)方法及其應(yīng)用[J];電力系統(tǒng)自動(dòng)化;2001年22期

2 顧潔;應(yīng)用小波分析進(jìn)行短期負(fù)荷預(yù)測(cè)[J];電力系統(tǒng)及其自動(dòng)化學(xué)報(bào);2003年02期

3 張林;羅曉初;徐瑞林;趙理;;基于時(shí)間序列的電力負(fù)荷預(yù)測(cè)新算法研究[J];電網(wǎng)技術(shù);2006年S2期

4 閆承山,劉永奇;人工神經(jīng)網(wǎng)絡(luò)在華北電網(wǎng)負(fù)荷預(yù)測(cè)中的應(yīng)用[J];電網(wǎng)技術(shù);1998年07期

5 李偉,韓力;組合灰色預(yù)測(cè)模型在電力負(fù)荷預(yù)測(cè)中的應(yīng)用[J];重慶大學(xué)學(xué)報(bào)(自然科學(xué)版);2004年01期

6 付寧杰;;提高撫州電網(wǎng)內(nèi)部市場(chǎng)負(fù)荷預(yù)測(cè)準(zhǔn)確率的措施[J];供電企業(yè)管理;2006年06期

7 韓哲;陳治平;熊斯毅;黎湖廣;;人工神經(jīng)網(wǎng)絡(luò)及其在電力短期負(fù)荷預(yù)測(cè)中的應(yīng)用研究[J];科學(xué)技術(shù)與工程;2009年05期

8 周林;呂厚軍;;人工神經(jīng)網(wǎng)絡(luò)應(yīng)用于電力系統(tǒng)短期負(fù)荷預(yù)測(cè)的研究[J];四川電力技術(shù);2008年06期

9 鄭崗,劉斌,周勇,劉丁,穆國(guó)強(qiáng);基于神經(jīng)元網(wǎng)絡(luò)的短期電力負(fù)荷預(yù)測(cè)[J];西安理工大學(xué)學(xué)報(bào);2002年02期

10 侯濤;電力系統(tǒng)中的人工智能方法及其應(yīng)用[J];云南電力技術(shù);2004年02期

本文編號(hào)：2314358