本文選題：季節(jié)性結(jié)構(gòu)時(shí)間序列模型　切入點(diǎn)：電力消費(fèi)特征　出處：《華僑大學(xué)》2017年碩士論文　論文類型：學(xué)位論文

【摘要】：在我國(guó),電力消費(fèi)是能源消費(fèi)的主要方式。一方面,電力消費(fèi)通常具有周期性和趨勢(shì)性兩種特征,如何合理并準(zhǔn)確刻畫(huà)電力消費(fèi)特征,一直以來(lái)是經(jīng)濟(jì)核算部門和一些科研機(jī)構(gòu)的重要研究課題之一。另一方面,在“十三五”電力規(guī)劃期間,國(guó)內(nèi)電力消費(fèi)情況面臨許多嚴(yán)峻挑戰(zhàn)。當(dāng)務(wù)之急是對(duì)未來(lái)的電力需求進(jìn)行預(yù)測(cè),如何準(zhǔn)確地預(yù)測(cè)我國(guó)電力消費(fèi)需求,實(shí)現(xiàn)經(jīng)濟(jì)平穩(wěn)增長(zhǎng),同樣也是一個(gè)重要研究課題之一。在這種大背景下,本文從一個(gè)新視角對(duì)我國(guó)電力消費(fèi)特征就測(cè)度和預(yù)測(cè)兩個(gè)方面進(jìn)行討論。本文從成分分解和狀態(tài)空間模型的角度,詳細(xì)介紹四種靜態(tài)STM的基本構(gòu)造方法理論,并應(yīng)用于我國(guó)電力消費(fèi)需求特征場(chǎng)景,對(duì)2005年至2016年我國(guó)電力季度消費(fèi)需求進(jìn)行特征測(cè)度,評(píng)選出最優(yōu)的靜態(tài)STM。之后在其基礎(chǔ)上進(jìn)行推廣,構(gòu)造固定參數(shù)形式的STM+βX模型和時(shí)變參數(shù)形式的tSTM+β_1X,應(yīng)用于我國(guó)電力消費(fèi)需求預(yù)測(cè)場(chǎng)景,對(duì)2016年電力消費(fèi)做出預(yù)測(cè)。最后對(duì)比STM+X和靜態(tài)STM,基于最優(yōu)模型選取指標(biāo),從擬合效果和預(yù)測(cè)精度兩個(gè)維度比較這幾種STM的模型效果。本文的主要結(jié)論主要有:第一,通過(guò)構(gòu)造Ⅰ(1)和Ⅰ(2)過(guò)程兩種趨勢(shì)成分形式,季節(jié)虛擬變量和季節(jié)三角函數(shù)兩種季節(jié)成分形式,通過(guò)兩兩組合構(gòu)造出四種狀態(tài)空間形式的靜態(tài)STM模型,利用極大似然法對(duì)超參數(shù)進(jìn)行估計(jì),刻畫(huà)出四種我國(guó)電力消費(fèi)需求特征。這四種靜態(tài)STM較好地刻畫(huà)了我國(guó)電力消費(fèi)特征,表明我國(guó)電力消費(fèi)具有趨勢(shì)性和季節(jié)性兩種特征。根據(jù)四種誤差評(píng)估指標(biāo)結(jié)果,發(fā)現(xiàn)Ⅰ(2)過(guò)程趨勢(shì)成分加時(shí)變季節(jié)三角函數(shù)的季節(jié)成分組合的靜態(tài)STM模型,能夠非常好地刻畫(huà)我國(guó)電力消費(fèi)的季節(jié)性特征。第二,在特征測(cè)度方面得到最優(yōu)的靜態(tài)STM模型的基礎(chǔ)上,對(duì)模型進(jìn)行推廣,得到固定參數(shù)形式的STM+βX和時(shí)變參數(shù)形式的tSTM+β_1X兩種狀態(tài)模型框架下的季節(jié)性STM+X模型,引入經(jīng)濟(jì)增長(zhǎng)和氣候因素兩種外生變量,先利用極大似然法對(duì)超參數(shù)進(jìn)行估計(jì),再利用這兩種STM+X模型刻畫(huà)電力消費(fèi)特征。這兩種STM+X也同時(shí)能很好的刻畫(huà)出我國(guó)電力消費(fèi)需求特征,根據(jù)四種誤差評(píng)估指標(biāo)結(jié)果,發(fā)現(xiàn)時(shí)變參數(shù)形式的tSTM+β_1X在擬合和預(yù)測(cè)兩方面都具有顯著的優(yōu)勢(shì),即電力消費(fèi)在預(yù)測(cè)方面的最優(yōu)模型為Ⅰ(2)過(guò)程趨勢(shì)成分加時(shí)變季節(jié)三角函數(shù)組合的時(shí)變參數(shù)tSTM+β_1X模型。第三,實(shí)證研究結(jié)果表明,我國(guó)電力消費(fèi)需求具有穩(wěn)定的內(nèi)在增長(zhǎng)趨勢(shì),同時(shí)容易受到外部沖擊的影響。此外,我國(guó)電力消費(fèi)需求還具有明顯的季節(jié)效應(yīng),受全球氣候變暖的影響,這種季節(jié)效應(yīng)還存在顯著的季節(jié)擴(kuò)張性。第四,實(shí)證研究結(jié)果表明,我國(guó)電力消費(fèi)還受我國(guó)宏觀經(jīng)濟(jì)內(nèi)生性發(fā)展和我國(guó)氣候條件程度決定。同時(shí),經(jīng)濟(jì)增長(zhǎng)和氣候條件對(duì)我國(guó)電力消費(fèi)需求存在一定的沖擊效應(yīng),且這種沖擊效應(yīng)是時(shí)變的。
[Abstract]:In China, electricity consumption is the main way of energy consumption. On the one hand, electricity consumption usually has two characteristics: periodicity and trend. It has always been one of the important research topics for economic accounting departments and some scientific research institutions. On the other hand, during the 13th Five-Year Plan, The domestic electric power consumption is facing many severe challenges. The urgent task is to forecast the future power demand, how to accurately forecast our country's electricity consumption demand, and how to realize the steady economic growth. It is also one of the important research topics. Under this background, this paper discusses the measurement and prediction of the characteristics of power consumption in China from a new perspective. This paper introduces in detail the basic construction method theory of four static STM, and applies them to the feature scenario of electric power consumption demand in our country, and measures the characteristics of our country's electric power quarterly consumption demand from 2005 to 2016. The optimal static STM is selected. Then the STM 尾 X model with fixed parameters and the tSTM 尾 1X with time-varying parameters are constructed on the basis of this model, which is applied to the power consumption demand prediction in China. Finally, compared with STM X and static STM, the model effects of these STM are compared from two dimensions of fitting effect and prediction precision based on the optimal model selection index. The main conclusions of this paper are as follows: first, By constructing two kinds of trend component forms, seasonal virtual variable and seasonal trigonometric function, the static STM model of four state space forms is constructed by constructing two kinds of trend component forms in the process of 鈪，

本文編號(hào)：1627026