【摘要】：短期負(fù)荷預(yù)測(cè)(Short-term load forecasting,STLF)是對(duì)未來(lái)若干小時(shí)、1天至幾天的電力負(fù)荷預(yù)報(bào),作為安排發(fā)購(gòu)電計(jì)劃,經(jīng)濟(jì)分配負(fù)荷及安排機(jī)組出力的基礎(chǔ),精準(zhǔn)的負(fù)荷預(yù)測(cè)是保證電網(wǎng)安全可靠運(yùn)行的前提條件。隨著居民生活水平的提高,能源消耗加大,調(diào)溫負(fù)荷占總用電負(fù)荷的比重日益增長(zhǎng),導(dǎo)致電網(wǎng)氣象敏感負(fù)荷不斷上升,從而構(gòu)成用電峰荷,拉大了電網(wǎng)峰谷差,現(xiàn)有的短期負(fù)荷預(yù)測(cè)技術(shù)在應(yīng)對(duì)復(fù)雜氣象條件時(shí)預(yù)測(cè)精度難以滿足電網(wǎng)要求。為落實(shí)電網(wǎng)對(duì)負(fù)荷精細(xì)化管理的要求,進(jìn)一步提高電網(wǎng)負(fù)荷預(yù)測(cè)的精細(xì)化水平,確保電網(wǎng)安全穩(wěn)定運(yùn)行,研究能真實(shí)反映負(fù)荷變化規(guī)律的負(fù)荷預(yù)測(cè)模型,對(duì)于提高短期負(fù)荷預(yù)測(cè)精度十分有必要。自邁入電力大數(shù)據(jù)時(shí)代以來(lái),系統(tǒng)原始運(yùn)行數(shù)據(jù)的存量增加,電力負(fù)荷預(yù)測(cè)技術(shù)與相關(guān)科學(xué)領(lǐng)域技術(shù),如氣象、經(jīng)濟(jì)等的交叉滲透。不可置否,大數(shù)據(jù)將是未來(lái)電網(wǎng)的生產(chǎn)力,因此在短期負(fù)荷預(yù)測(cè)領(lǐng)域深度挖掘氣象、負(fù)荷大數(shù)據(jù)的價(jià)值,是融合大能源思維與大數(shù)據(jù)思維研究考慮多因素氣象的負(fù)荷預(yù)測(cè)建模,實(shí)現(xiàn)電力負(fù)荷精細(xì)化管理,提高短期負(fù)荷預(yù)測(cè)精度不可或缺的一部分。本文在電力大數(shù)據(jù)的基礎(chǔ)上,本文首先分析了考慮多因素氣象的負(fù)荷特性,從年周期、季周期、日周期等時(shí)間維度以及氣象的特殊性方面剖析了氣象對(duì)負(fù)荷的影響。針對(duì)氣象變化時(shí)負(fù)荷曲線預(yù)測(cè)精度低,預(yù)測(cè)模型不能完全適應(yīng)氣象變化的情況,本文提出了一種提出了完全氣象因子序列的概念,基于數(shù)據(jù)挖掘的方法建立氣象粒化集;采用空間多元回歸及滯后模型結(jié)合多策略靈敏度分析法,建立了針對(duì)復(fù)雜氣象條件下的曲線拐點(diǎn)預(yù)測(cè)模型;基于改進(jìn)的K-means聚類分析法查找并獲取氣象特征日,計(jì)算初步預(yù)測(cè)曲線,主動(dòng)判斷預(yù)測(cè)曲線畸變概率并進(jìn)行優(yōu)化修正,得到最佳預(yù)測(cè)負(fù)荷曲線。為應(yīng)對(duì)氣象突變對(duì)負(fù)荷曲線的影響提出了基于多粒度氣象信息匹配的曲線修正模型,針對(duì)突變氣象進(jìn)行曲線修正。最后利用動(dòng)態(tài)數(shù)據(jù)流對(duì)模型參數(shù)進(jìn)行更新,實(shí)現(xiàn)精細(xì)化預(yù)測(cè)。最后采用本文方法對(duì)我國(guó)南方某地區(qū)全年負(fù)荷曲線進(jìn)行預(yù)測(cè),驗(yàn)證了模型在多種氣象條件下的預(yù)測(cè)準(zhǔn)確性,尤其適用于短期內(nèi)氣象存在復(fù)雜變化的情形。
[Abstract]:Short-term load forecasting (STLF) is a power load forecast for the next few hours or days, which serves as the basis for arranging generation and purchase plans, economic load distribution and generating units. Accurate load forecasting is the precondition to ensure the safe and reliable operation of power grid. With the improvement of residents' living standard, energy consumption is increasing, and the proportion of temperature adjustment load to total power load is increasing day by day, which leads to the rising of meteorological sensitive load of power grid, which forms the peak load of electricity consumption and widens the difference between peak and valley of power grid. The existing short-term load forecasting technology is difficult to meet the requirements of power grid when dealing with complex meteorological conditions. In order to meet the requirement of fine load management, to improve the precision of load forecasting, to ensure the safe and stable operation of power network, a load forecasting model which can truly reflect the law of load change is studied. It is necessary to improve the accuracy of short-term load forecasting. Since entering the era of electric power big data, the stock of the original operation data of the system has increased, and the interpenetration of power load forecasting technology and related scientific fields, such as meteorology, economy, etc. Big data will be the productivity of power grid in the future. Therefore, in the field of short-term load forecasting, the value of load big data is a combination of large energy thinking and big data thinking research, considering multi-factor meteorological load forecasting modeling. It is an indispensable part to realize the fine management of power load and improve the precision of short-term load forecasting. Based on the big data of electric power, this paper first analyzes the load characteristics of multi-factor meteorology, and analyzes the influence of meteorology on the load from the time dimension of annual cycle, season period, daily period and the particularity of meteorology. Because the forecasting precision of load curve is low and the forecasting model can not adapt to the situation of meteorological change, a concept of complete meteorological factor series is put forward in this paper, and the meteorological granulation set is established based on data mining method. By using spatial multivariate regression and lag model combined with multi-strategy sensitivity analysis, the curve inflection point prediction model for complex meteorological conditions is established, and the weather feature days are found and obtained based on improved K-means clustering analysis. The preliminary prediction curve is calculated, the distortion probability of the prediction curve is judged and the optimal load forecasting curve is obtained. In order to deal with the influence of meteorological catastrophe on load curve, a curve correction model based on multi-granularity meteorological information matching is proposed. Finally, the dynamic data stream is used to update the model parameters to achieve fine prediction. Finally, the method of this paper is used to forecast the annual load curve in a certain area of southern China, which verifies the accuracy of the model under various meteorological conditions, especially in the case of complex meteorological changes in the short term.
【學(xué)位授予單位】：廣西大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：TM715

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 李培強(qiáng);李慧;李欣然;;基于靈敏度與相關(guān)性的綜合負(fù)荷模型參數(shù)優(yōu)化辨識(shí)策略[J];電工技術(shù)學(xué)報(bào);2016年16期

2 薛禹勝;賴業(yè)寧;;大能源思維與大數(shù)據(jù)思維的融合 (二)應(yīng)用及探索[J];電力系統(tǒng)自動(dòng)化;2016年08期

3 吳茵;張智光;苗增強(qiáng);龔利武;黃柳強(qiáng);覃芳璐;李濱;;基于標(biāo)幺化負(fù)荷靈敏度的夏季空調(diào)負(fù)荷計(jì)算[J];電網(wǎng)與清潔能源;2016年02期

4 吳茵;張智光;楊小衛(wèi);龔利武;苗增強(qiáng);覃芳璐;李濱;;考慮氣象因素的冬季取暖負(fù)荷計(jì)算[J];電網(wǎng)與清潔能源;2016年01期

5 薛禹勝;賴業(yè)寧;;大能源思維與大數(shù)據(jù)思維的融合(一)大數(shù)據(jù)與電力大數(shù)據(jù)[J];電力系統(tǒng)自動(dòng)化;2016年01期

6 王繼業(yè);;大數(shù)據(jù):電網(wǎng)企業(yè)創(chuàng)新發(fā)展驅(qū)動(dòng)力[J];國(guó)家電網(wǎng);2015年12期

7 黃歸蘭;趙宇;馬繼華;王慶國(guó);陳陽(yáng);;廣西氣象災(zāi)害預(yù)警信號(hào)分布特征及發(fā)布[J];氣象科技;2015年02期

8 計(jì)鹿飛;江琦;唐昊;譚琦;;基于半馬爾可夫控制過(guò)程的智能電網(wǎng)最優(yōu)儲(chǔ)能控制[J];電力系統(tǒng)自動(dòng)化;2015年06期

9 肖勇;楊勁鋒;馬千里;闕華坤;王家兵;秦州;;基于模塊化回聲狀態(tài)網(wǎng)絡(luò)的實(shí)時(shí)電力負(fù)荷預(yù)測(cè)[J];電網(wǎng)技術(shù);2015年03期

10 高賜威;李倩玉;蘇衛(wèi)華;李揚(yáng);;短期負(fù)荷預(yù)測(cè)中考慮積溫效應(yīng)的溫度修正模型研究[J];電工技術(shù)學(xué)報(bào);2015年04期

相關(guān)重要報(bào)紙文章 前2條

1 李婕茜;;讓大數(shù)據(jù)物盡其用[N];國(guó)家電網(wǎng)報(bào);2016年

2 唐金生;;精細(xì)化管理是這樣煉成的[N];國(guó)家電網(wǎng)報(bào);2007年

相關(guān)碩士學(xué)位論文 前3條

1 余威;氣象相似性網(wǎng)絡(luò)構(gòu)建及缺失氣象要素?cái)?shù)據(jù)的插補(bǔ)[D];西南大學(xué);2015年

2 石雪;基于數(shù)據(jù)挖掘的短期電力負(fù)荷預(yù)測(cè)[D];華南理工大學(xué);2014年

3 劉凱;基于改進(jìn)BP神經(jīng)網(wǎng)絡(luò)的短期負(fù)荷預(yù)測(cè)研究[D];河海大學(xué);2005年

，

本文編號(hào)：2126880