發(fā)布時間：2018-06-07 04:39

  本文選題：負(fù)荷預(yù)測 + 數(shù)據(jù)預(yù)處理　； 參考：《西安理工大學(xué)》2017年碩士論文

【摘要】：電刀系統(tǒng)短期負(fù)荷預(yù)測意義深遠(yuǎn),是系統(tǒng)優(yōu)化運(yùn)行的基礎(chǔ),負(fù)荷預(yù)測結(jié)果對系統(tǒng)的經(jīng)濟(jì)與安全有重要意義。目前有很多種方法可以進(jìn)行負(fù)荷預(yù)測,但是人們?nèi)匀幌Ｍ玫礁呔鹊念A(yù)測結(jié)果。因此,探索研究快速、準(zhǔn)確的負(fù)荷預(yù)測方法有很大意義。本文詳細(xì)介紹了電力系統(tǒng)短期負(fù)荷預(yù)測的研究內(nèi)容,總結(jié)了國內(nèi)外負(fù)荷預(yù)測的方法,分析了各預(yù)測方法的優(yōu)缺點(diǎn)。分析了傳統(tǒng)的神經(jīng)網(wǎng)絡(luò)預(yù)測算法的不足,提出了貓群算法優(yōu)化BP神經(jīng)網(wǎng)絡(luò)的組合算法,本文的內(nèi)容主要包括以下個方面:分析了美國某地的負(fù)荷特性,總結(jié)了負(fù)荷的周期特點(diǎn)和節(jié)假日特性,分析了影響負(fù)荷的各種因素與負(fù)荷之間的關(guān)系。介紹了歷史負(fù)荷數(shù)據(jù)中不良數(shù)據(jù)的成因與對負(fù)荷預(yù)測的影響,采用改良后的模糊c-均值聚類算法對日負(fù)荷曲線進(jìn)行聚類,得到若干特征曲線,通過負(fù)荷的橫向相似性找出不良數(shù)據(jù);最后對不良數(shù)據(jù)進(jìn)行修正。修正不良數(shù)據(jù),消除負(fù)荷曲線毛刺。建立了考慮日特征相關(guān)因素的BP神經(jīng)網(wǎng)絡(luò)負(fù)荷預(yù)測模型。以歷史時刻的溫度、負(fù)荷、星期類型歸一化后作為BP神經(jīng)網(wǎng)絡(luò)預(yù)測模型的輸入變量。介紹了貓群算法,測試函數(shù)表明貓群算法相比與遺傳算法收斂更快且不易陷入局部最優(yōu)解。為克服神經(jīng)網(wǎng)絡(luò)收斂速度慢,網(wǎng)絡(luò)初始值選取不當(dāng)而陷入局部極小點(diǎn)的缺點(diǎn),提高電力系統(tǒng)短期負(fù)荷預(yù)測精度,將貓群算法和BP神經(jīng)網(wǎng)絡(luò)結(jié)合,提出基于貓群-BP神經(jīng)網(wǎng)絡(luò)的短期負(fù)荷預(yù)測模型。用貓群算法優(yōu)化BP神經(jīng)網(wǎng)絡(luò)的權(quán)值和閾值,避免神經(jīng)網(wǎng)絡(luò)初始權(quán)值選取的盲目性,訓(xùn)練BP神經(jīng)網(wǎng)絡(luò)預(yù)測模型求得最優(yōu)解。算例表明,貓群優(yōu)化的BP神經(jīng)網(wǎng)絡(luò)有效改善了 BP神經(jīng)網(wǎng)絡(luò)的缺點(diǎn),提高了神經(jīng)網(wǎng)絡(luò)用于電力系統(tǒng)短期負(fù)荷預(yù)測精度的效率和精度。相比于遺傳神經(jīng)網(wǎng)絡(luò),該方法預(yù)測精度更高,收斂更快,具有一定的實用性。
[Abstract]:The short-term load forecasting of the electric knife system is of far-reaching significance and is the basis of the optimal operation of the system. The result of the load forecasting is of great significance to the economy and safety of the system. At present, there are many methods for load forecasting, but people still want to get more accurate forecasting results. Therefore, it is of great significance to explore fast and accurate load forecasting methods. This paper introduces the research contents of short-term load forecasting in power system, summarizes the methods of load forecasting at home and abroad, and analyzes the advantages and disadvantages of each forecasting method. In this paper, the shortcomings of the traditional neural network prediction algorithm are analyzed, and the combination algorithm of the cat swarm optimization BP neural network is proposed. The main contents of this paper include the following aspects: the load characteristics of a certain place in the United States are analyzed. The periodic and holiday characteristics of load are summarized, and the relationship between various factors affecting load and load is analyzed. This paper introduces the causes of bad data in historical load data and its influence on load forecasting. The improved fuzzy c-means clustering algorithm is used to cluster the daily load curve, and some characteristic curves are obtained. Through the lateral similarity of load to find out the bad data, and finally to correct the bad data. Correct bad data and eliminate burr of load curve. A BP neural network load forecasting model considering the correlation factors of daily characteristics is established. The temperature load and week type of historical time are normalized as input variables of BP neural network prediction model. The cat swarm algorithm is introduced. The test function shows that the cat swarm algorithm converges faster than the genetic algorithm and is not easy to fall into the local optimal solution. In order to overcome the shortcomings of slow convergence speed of neural network and improper selection of initial value of neural network, and to improve the accuracy of short-term load forecasting in power system, the cat swarm algorithm and BP neural network are combined. A short term load forecasting model based on cat swarm BP neural network is proposed. The weight and threshold of BP neural network are optimized by using cat swarm algorithm to avoid blindness of selecting initial weight of neural network, and BP neural network prediction model is trained to obtain the optimal solution. The examples show that the BP neural network based on cat swarm optimization can effectively improve the shortcomings of BP neural network and improve the efficiency and accuracy of the neural network used in short-term load forecasting of power system. Compared with genetic neural network, this method has higher prediction accuracy, faster convergence and better practicability.
【學(xué)位授予單位】：西安理工大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2017
【分類號】：TM715

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 唐宏;馮平;陳鏡伯;陳杰睿;朱建疆;;螢火蟲算法優(yōu)化SVR參數(shù)在短期電力負(fù)荷預(yù)測中的應(yīng)用[J];西華大學(xué)學(xué)報(自然科學(xué)版);2017年01期

2 焦李成;楊淑媛;劉芳;王士剛;馮志璽;;神經(jīng)網(wǎng)絡(luò)七十年:回顧與展望[J];計算機(jī)學(xué)報;2016年08期

3 王保義;王冬陽;張少敏;;基于Spark和IPPSO_LSSVM的短期分布式電力負(fù)荷預(yù)測算法[J];電力自動化設(shè)備;2016年01期

4 張淑清;師榮艷;董玉蘭;李盼;任爽;姜萬錄;;雙變量小波閾值去噪和改進(jìn)混沌預(yù)測模型在短期電力負(fù)荷預(yù)測中的應(yīng)用[J];中國電機(jī)工程學(xué)報;2015年22期

5 張振;王鋒;陳敏曦;;基于BP網(wǎng)絡(luò)的電力負(fù)荷預(yù)測改進(jìn)研究[J];中國電業(yè)(技術(shù)版);2015年10期

6 王永弟;孫心宇;;貓群優(yōu)化算法的非線性模型參數(shù)估計[J];測繪科學(xué);2015年09期

7 吳偉林;周永華;;基于差分演化與貓群算法融合的群體智能算法[J];計算技術(shù)與自動化;2014年04期

8 楊淑瑩;劉旭鵬;陶沖;劉婷婷;;基于免疫貓群優(yōu)化算法的矢量量化的碼書設(shè)計及語音識別[J];模式識別與人工智能;2014年07期

9 馬知也;施秋紅;;貓群算法研究綜述[J];甘肅廣播電視大學(xué)學(xué)報;2014年02期

10 王保義;趙碩;張少敏;;基于云計算和極限學(xué)習(xí)機(jī)的分布式電力負(fù)荷預(yù)測算法[J];電網(wǎng)技術(shù);2014年02期

相關(guān)博士學(xué)位論文 前1條

1 趙鳴;簡潔式群智能計算及應(yīng)用研究[D];哈爾濱工業(yè)大學(xué);2015年

相關(guān)碩士學(xué)位論文 前6條

1 李艷玲;基于神經(jīng)網(wǎng)絡(luò)的電力系統(tǒng)負(fù)荷預(yù)測問題研究[D];沈陽工業(yè)大學(xué);2014年

2 王樂;基于灰色理論和神經(jīng)網(wǎng)絡(luò)的電力系統(tǒng)短期負(fù)荷預(yù)測研究及其比較[D];廣西大學(xué);2012年

3 張鑫;基于數(shù)值分析的改進(jìn)GM（1，1）負(fù)荷預(yù)測模型研究[D];太原理工大學(xué);2012年

4 呂嬋;基于BP神經(jīng)網(wǎng)絡(luò)的短期負(fù)荷預(yù)測[D];華中科技大學(xué);2007年

5 張h;FCM算法初始化方法研究[D];西南大學(xué);2006年

6 王晨楓;電力系統(tǒng)負(fù)荷預(yù)測的技術(shù)研究[D];大慶石油學(xué)院;2003年

，

本文編號：1989823