【摘要】：隨著我國經(jīng)濟(jì)的快速發(fā)展,能源枯竭問題日益加重,微網(wǎng)作為一種清潔友好型能源,能夠利用當(dāng)?shù)氐馁Y源優(yōu)勢,有效解決我國中西部偏遠(yuǎn)地區(qū)用電難、電能運(yùn)輸成本高、利用率低等問題。而微網(wǎng)短期負(fù)荷預(yù)測作為微網(wǎng)中的研究熱點(diǎn),日益受到研究人員的關(guān)注。對微網(wǎng)短期負(fù)荷進(jìn)行有效預(yù)測,能夠為微網(wǎng)系統(tǒng)節(jié)能高效的運(yùn)行提供保障、為電力調(diào)度部門制定發(fā)電計劃提供依據(jù)。因此加強(qiáng)微網(wǎng)的負(fù)荷預(yù)測無論對微網(wǎng)系統(tǒng)本身還是對大電網(wǎng)都有重要的意義。本文針對微網(wǎng)負(fù)荷的特點(diǎn),提出了基于數(shù)據(jù)挖掘和遺傳模擬退火算法(GSA算法)優(yōu)化的多模型神經(jīng)網(wǎng)絡(luò)微網(wǎng)短期負(fù)荷預(yù)測模型。主要研究工作以及創(chuàng)新性內(nèi)容如下:首先,對影響微網(wǎng)負(fù)荷的氣象、日類型以及實際歷史負(fù)荷等因素進(jìn)行分析,根據(jù)這些因素建立微網(wǎng)負(fù)荷預(yù)測的初步樣本數(shù)據(jù),利用數(shù)據(jù)挖掘技術(shù)對該樣本數(shù)據(jù)進(jìn)行挖掘處理,并建立基本預(yù)測模型。具體處理方法為:(1)利用粗糙集屬性約簡算法對樣本數(shù)據(jù)進(jìn)行約簡處理,找到影響微網(wǎng)負(fù)荷的核心因素,并將其作為預(yù)測模型的輸入;(2)針對微網(wǎng)負(fù)荷的波動性、隨機(jī)性等特點(diǎn),對約簡后的樣本數(shù)據(jù)進(jìn)行模糊聚類分析,將樣本數(shù)據(jù)分為若干類,并針對每一類樣本建立對應(yīng)的BP神經(jīng)網(wǎng)絡(luò)預(yù)測模型;(3)在對微網(wǎng)負(fù)荷進(jìn)行預(yù)測時,通過模式識別技術(shù)尋找與預(yù)測日最近的樣本集合對應(yīng)的網(wǎng)絡(luò),并利用此網(wǎng)絡(luò)對微網(wǎng)負(fù)荷進(jìn)行預(yù)測。通過以上幾步建立了基于多模型BP網(wǎng)絡(luò)的微網(wǎng)短期負(fù)荷預(yù)測模型。通過仿真對比,驗證了預(yù)測模型能夠取得理想的預(yù)測結(jié)果。其次,針對BP神經(jīng)網(wǎng)絡(luò)迭代速度慢、易陷入局部極小值等缺陷,提出了基于GSA算法優(yōu)化的多模型BP網(wǎng)絡(luò)預(yù)測模型,將遺傳算法(GA)的并行搜索結(jié)構(gòu)和模擬退火算法(SA)的概率突跳特性與BP網(wǎng)絡(luò)相結(jié)合,對微網(wǎng)負(fù)荷做出預(yù)測。將優(yōu)化后的預(yù)測模型與優(yōu)化前的預(yù)測模型做對比,結(jié)果表明,優(yōu)化后的模型預(yù)測精度更高。并且通過與其他預(yù)測算法比較,進(jìn)一步驗證了GSA算法優(yōu)化的多模型BP網(wǎng)絡(luò)在微網(wǎng)短期負(fù)荷預(yù)測中的優(yōu)勢。最后,通過分析國外微網(wǎng)負(fù)荷的運(yùn)行情況發(fā)現(xiàn),實時電價因素在一定程度上會影響微網(wǎng)負(fù)荷的大小。因此,本文將實時電價因素引入預(yù)測模型中。利用模糊控制算法對模型預(yù)測后的微網(wǎng)負(fù)荷值進(jìn)行修正。仿真結(jié)果表明,該算法能夠?qū)紤]實時電價因素的預(yù)測結(jié)果進(jìn)行有效地修正。
[Abstract]:With the rapid development of economy in our country, the problem of energy depletion is getting worse and worse. As a kind of clean and friendly energy, microgrid can effectively solve the problem of electricity utilization in remote areas of central and western China, and the cost of electricity transportation is high. Low utilization rate and other problems. Microgrid short-term load forecasting, as a research hotspot in micro-grid, has been paid more and more attention by researchers. The short-term load forecasting of microgrid can provide the guarantee for the energy saving and efficient operation of the micro-grid system, and provide the basis for the power dispatching department to formulate the generation plan. Therefore, it is of great significance to strengthen the load forecasting of microgrid for both microgrid system and large power grid. According to the characteristics of microgrid load, a multi-model neural network short-term load forecasting model based on data mining and genetic simulated annealing algorithm (GSA) is proposed in this paper. The main research work and innovative contents are as follows: firstly, the factors affecting microgrid load, such as meteorology, daily type and actual historical load, are analyzed, and the preliminary sample data of microgrid load forecasting are established according to these factors. The data mining technology is used to mine the sample data, and the basic prediction model is established. The specific processing methods are as follows: (1) the rough set attribute reduction algorithm is used to reduce the sample data to find the core factors that affect the load of the microgrid and take it as the input of the prediction model; (2) according to the characteristics of volatility and randomness of microgrid load, the reduced sample data is analyzed by fuzzy clustering, and the sample data is divided into several categories, and the corresponding BP neural network prediction model is established for each kind of sample. (3) in forecasting the load of microgrid, the pattern recognition technique is used to find the network corresponding to the nearest sample set on the forecasting day, and the network is used to forecast the load of microgrid. The short term load forecasting model of micro grid based on multi-model BP network is established through the above steps. The simulation results show that the prediction model can obtain ideal prediction results. Secondly, aiming at the shortcomings of BP neural network, such as slow iterative speed and easy to fall into local minimum, a multi-model BP network prediction model based on GSA algorithm optimization is proposed. The parallel search structure of genetic algorithm (GA) and the probabilistic jump characteristics of simulated annealing algorithm (SA) are combined with BP network to predict the load of microgrid. The results show that the precision of the optimized model is higher than that of the optimized model. Compared with other prediction algorithms, the advantages of multi-model BP network optimized by GSA algorithm in short-term load forecasting of microgrid are further verified. Finally, by analyzing the operation of microgrid load in foreign countries, it is found that the real time price factor will affect the load of microgrid to some extent. Therefore, this paper introduces the real-time electricity price factor into the prediction model. The fuzzy control algorithm is used to modify the load value of the microgrid after the model prediction. The simulation results show that the algorithm can effectively modify the prediction results considering the real-time price factors.
【學(xué)位授予單位】：中國礦業(yè)大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2017
【分類號】：TP311.13;TP18;TM715

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 齊庭庭;李建奇;;基于改進(jìn)機(jī)器學(xué)習(xí)算法的微電網(wǎng)短期負(fù)荷預(yù)測[J];湖南文理學(xué)院學(xué)報(自然科學(xué)版);2016年03期

2 許志榮;楊蘋;趙卓立;王燦;;中國多微網(wǎng)系統(tǒng)發(fā)展分析[J];電力系統(tǒng)自動化;2016年17期

3 張彥宇;肖茜;;國內(nèi)外關(guān)于電力系統(tǒng)負(fù)荷預(yù)測的研究現(xiàn)狀分析[J];山東工業(yè)技術(shù);2016年11期

4 林順富;郝朝;湯曉棟;李東東;符楊;;基于數(shù)據(jù)挖掘的樓宇短期負(fù)荷預(yù)測方法研究[J];電力系統(tǒng)保護(hù)與控制;2016年07期

5 于洪;王國胤;姚一豫;;決策粗糙集理論研究現(xiàn)狀與展望[J];計算機(jī)學(xué)報;2015年08期

6 盧鶴挺;;基于多元線性回歸分析的用電量研究[J];中國新技術(shù)新產(chǎn)品;2015年14期

7 李東東;覃子珊;林順富;鄭小霞;王天祥;;基于混沌時間序列法的微網(wǎng)短期負(fù)荷預(yù)測[J];電力系統(tǒng)及其自動化學(xué)報;2015年05期

8 劉念;張清鑫;劉海濤;;基于核函數(shù)極限學(xué)習(xí)機(jī)的微電網(wǎng)短期負(fù)荷預(yù)測方法[J];電工技術(shù)學(xué)報;2015年08期

9 張玲玲;楊明玉;梁武;;微網(wǎng)用戶短期負(fù)荷預(yù)測相似日選擇算法[J];中國電力;2015年04期

10 趙慧材;陳躍輝;陳瑞先;彭子揚(yáng);;結(jié)合模糊粗糙集和支持向量機(jī)的電力負(fù)荷短期預(yù)測方法[J];中國電力;2015年02期

相關(guān)博士學(xué)位論文 前2條

1 王快妮;支持向量機(jī)魯棒性模型與算法研究[D];中國農(nóng)業(yè)大學(xué);2015年

2 王鶴;含多種分布式電源的微電網(wǎng)運(yùn)行控制研究[D];華北電力大學(xué);2014年

相關(guān)碩士學(xué)位論文 前10條

1 廖祥賓;基于碳排放約束的能源消費(fèi)結(jié)構(gòu)優(yōu)化研究[D];江南大學(xué);2016年

2 趙洋;基于數(shù)據(jù)挖掘技術(shù)的南京地區(qū)短期電力負(fù)荷預(yù)測方法研究[D];華北電力大學(xué);2016年

3 畢圣;基于數(shù)據(jù)挖掘技術(shù)的短期負(fù)荷預(yù)測[D];北京交通大學(xué);2016年

4 王艷龍;基于數(shù)據(jù)挖掘的中長期電力市場需求分析及預(yù)測[D];浙江大學(xué);2016年

5 趙晶;城市電力負(fù)荷預(yù)測技術(shù)及其在通遼電網(wǎng)中的應(yīng)用[D];華北電力大學(xué);2015年

6 杜明建;大數(shù)據(jù)技術(shù)在負(fù)荷預(yù)測與負(fù)荷特性分析中的應(yīng)用[D];東南大學(xué);2015年

7 楊屹洲;基于數(shù)據(jù)挖掘的商業(yè)電力負(fù)荷預(yù)測及用電優(yōu)化算法研究[D];華僑大學(xué);2015年

8 楊波;基于支持向量機(jī)的電力系統(tǒng)短期負(fù)荷預(yù)測[D];遼寧工業(yè)大學(xué);2015年

9 匙躍軍;曲陽地區(qū)中長期電力負(fù)荷預(yù)測研究[D];華北電力大學(xué);2015年

10 楊育剛;基于光伏發(fā)電與負(fù)荷預(yù)測的微電網(wǎng)儲能系統(tǒng)控制策略研究[D];華北電力大學(xué);2015年

，

本文編號：2323341