【摘要】：電力系統(tǒng)短期負(fù)荷預(yù)測(cè)是電網(wǎng)安全、經(jīng)濟(jì)運(yùn)行的重要依據(jù)之一，正確而精準(zhǔn)的電力系統(tǒng)短期負(fù)荷預(yù)測(cè)有助于提高電網(wǎng)運(yùn)行的安全性、經(jīng)濟(jì)性和改善電能質(zhì)量。因此，尋求最合適的電力短期負(fù)荷預(yù)測(cè)的預(yù)測(cè)方法，從而對(duì)提高短期負(fù)荷預(yù)測(cè)的預(yù)測(cè)精度是具有十分重要的應(yīng)用價(jià)值。 本文基于電力系統(tǒng)短期負(fù)荷預(yù)測(cè)的背景、意義以及國內(nèi)外發(fā)展現(xiàn)狀的研究，分析了電力系統(tǒng)負(fù)荷的特點(diǎn)、規(guī)律以及與各種影響因素之間的非線性關(guān)系，給出了對(duì)歷史負(fù)荷數(shù)據(jù)中異常數(shù)據(jù)的辨識(shí)與處理方法，對(duì)歷史負(fù)荷數(shù)據(jù)和與短期負(fù)荷預(yù)測(cè)有關(guān)的影響因素進(jìn)行歸一化處理。根據(jù)最小二乘支持向量機(jī)(LSSVM)具有能夠較好地解決小樣本、非線性、高維數(shù)以及局部極小值等實(shí)際問題的優(yōu)勢(shì)。首先基于支持向量機(jī)(SVM)的研究，通過利用訓(xùn)練誤差的平方代替松弛變量，將不等式約束改進(jìn)為等式約束，從而提出最小二乘支持向量機(jī)(LSSVM)的電力系統(tǒng)短期負(fù)荷預(yù)測(cè)模型，這樣就避免了求解一個(gè)二次規(guī)劃問題，提高預(yù)測(cè)模型訓(xùn)練的速度。 由于LSSVM短期負(fù)荷預(yù)測(cè)模型的參數(shù)選擇對(duì)預(yù)測(cè)結(jié)果精度有著至關(guān)重要的影響，，本文提出利用粒子群算法(PSO)對(duì)LSSVM中的參數(shù)進(jìn)行優(yōu)化選擇，得到基于PSO-LSSVM的短期負(fù)荷預(yù)測(cè)模型，以求進(jìn)一步提高預(yù)測(cè)精度。但在粒子群優(yōu)化算法進(jìn)行尋優(yōu)過程中，容易陷入局部最小值，出現(xiàn)早熟收斂的情況，針對(duì)這一問題，提出對(duì)標(biāo)準(zhǔn)粒子群優(yōu)化算法進(jìn)行改進(jìn)，避免其在優(yōu)化過程中出現(xiàn)上述問題。建立基于改進(jìn)粒子群優(yōu)化算法的最小二乘支持向量機(jī)(IPSO-LSSVM)短期負(fù)荷預(yù)測(cè)模型。并通過平均相對(duì)誤差和均方差根來作為評(píng)價(jià)標(biāo)準(zhǔn)，驗(yàn)證該算法的準(zhǔn)確性。 最后，本文通過對(duì)2010年廣東某地區(qū)的歷史負(fù)荷數(shù)據(jù)進(jìn)行分析研究，分別對(duì)基于LSSVM、PSO-LSSVM、IPSO-LSSVM的三種短期負(fù)預(yù)測(cè)模型進(jìn)行預(yù)測(cè)仿真。最終結(jié)果對(duì)比表明：IPSO-LSSVM短期負(fù)荷預(yù)測(cè)模型具有收斂性好、有較高的預(yù)測(cè)精度和較快的訓(xùn)練速度，驗(yàn)證利用改進(jìn)的PSO算法進(jìn)行參數(shù)優(yōu)化有助于提高短期負(fù)荷預(yù)測(cè)的預(yù)測(cè)精度，由此可以說明對(duì)LSSVM短期負(fù)荷預(yù)測(cè)模型的參數(shù)優(yōu)化具有很高的研究?jī)r(jià)值和社會(huì)意義。
[Abstract]:Short-term load forecasting of power system is one of the important bases for safe and economical operation of power system. Correct and accurate short-term load forecasting of power system is helpful to improve the security, economy and power quality of power system. Therefore, it is very important to find the most suitable short-term load forecasting method to improve the forecasting accuracy of short-term load forecasting. Based on the background and significance of short-term load forecasting in power system and the research on the development of power system at home and abroad, this paper analyzes the characteristics, laws and nonlinear relationship between power system load and various influencing factors. The identification and processing methods of abnormal data in historical load data are given. The historical load data and the influencing factors related to short-term load forecasting are normalized. According to the least squares support vector machine (LSSVM), it has the advantage of solving the practical problems such as small sample, nonlinear, high dimension and local minimum. Firstly, based on the research of support vector machine (SVM), the inequality constraint is improved to equality constraint by using the square of training error instead of relaxation variable, and a short-term load forecasting model of power system based on least squares support vector machine (LSSVM) is proposed. In this way, it avoids solving a quadratic programming problem and improves the training speed of prediction model. Because the parameter selection of LSSVM short-term load forecasting model has an important influence on the precision of forecasting results, this paper proposes to optimize the selection of parameters in LSSVM by using particle swarm optimization algorithm (PSO), and obtain the short-term load forecasting model based on PSO-LSSVM. In order to further improve the accuracy of prediction. However, in the process of particle swarm optimization, it is easy to fall into the local minimum, which leads to premature convergence. To solve this problem, an improved standard particle swarm optimization algorithm is proposed to avoid the above problems in the process of optimization. A short term load forecasting model based on improved particle swarm optimization (PSO) based on least squares support vector machine (IPSO-LSSVM) is established. The accuracy of the algorithm is verified by using the mean relative error and root of mean variance as evaluation criteria. Finally, by analyzing the historical load data of a certain area in Guangdong province in 2010, this paper simulates three short-term negative forecasting models based on LSSVMU PSO-LSSVMU IPSO-LSSVM respectively. The comparison of the final results shows that the short term load forecasting model has good convergence, high forecasting accuracy and fast training speed. It is proved that the improved PSO algorithm is helpful to improve the forecasting accuracy of short-term load forecasting. Therefore, it is of great value and social significance to optimize the parameters of LSSVM short-term load forecasting model.
【學(xué)位授予單位】：湖南大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2014
【分類號(hào)】：TM715

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 張國江,邱家駒,李繼紅;基于模糊推理系統(tǒng)的多因素電力負(fù)荷預(yù)測(cè)[J];電力系統(tǒng)自動(dòng)化;2002年05期

2 康重慶,夏清,張伯明;電力系統(tǒng)負(fù)荷預(yù)測(cè)研究綜述與發(fā)展方向的探討[J];電力系統(tǒng)自動(dòng)化;2004年17期

3 孟思齊;楊洪耕;;基于灰色生成的卡爾曼濾波短期負(fù)荷預(yù)測(cè)[J];電力系統(tǒng)及其自動(dòng)化學(xué)報(bào);2008年06期

4 甘文泉,胡保生;用自適應(yīng)神經(jīng)元網(wǎng)絡(luò)進(jìn)行短期電力負(fù)荷預(yù)測(cè)[J];電網(wǎng)技術(shù);1997年03期

5 梁海峰,涂光瑜,唐紅衛(wèi);遺傳神經(jīng)網(wǎng)絡(luò)在電力系統(tǒng)短期負(fù)荷預(yù)測(cè)中的應(yīng)用[J];電網(wǎng)技術(shù);2001年01期

6 劉旭;羅滇生;姚建剛;賀輝;張凱;劉霏;;基于負(fù)荷分解和實(shí)時(shí)氣象因素的短期負(fù)荷預(yù)測(cè)[J];電網(wǎng)技術(shù);2009年12期

7 趙宇紅;唐耀庚;張韻輝;;基于神經(jīng)網(wǎng)絡(luò)和模糊理論的短期負(fù)荷預(yù)測(cè)[J];高電壓技術(shù);2006年05期

8 楊帆;吳耀武;熊信銀;婁素華;彭豐;;用自適應(yīng)模糊推理系統(tǒng)預(yù)測(cè)電力短期負(fù)荷[J];高電壓技術(shù);2007年04期

9 馬潔;韓蘊(yùn)韜;李國斌;;基于自回歸模型的船舶姿態(tài)運(yùn)動(dòng)預(yù)報(bào)[J];艦船科學(xué)技術(shù);2006年03期

10 李明干,孫健利,劉沛;基于卡爾曼濾波的電力系統(tǒng)短期負(fù)荷預(yù)測(cè)[J];繼電器;2004年04期

本文編號(hào)：2170322