【摘要】：提高空調(diào)負(fù)荷預(yù)測(cè)的準(zhǔn)確性是實(shí)現(xiàn)空調(diào)系統(tǒng)節(jié)能運(yùn)行和優(yōu)化控制的基礎(chǔ)和前提條件。針對(duì)現(xiàn)有空調(diào)負(fù)荷預(yù)測(cè)算法精度和速度難以滿足空調(diào)系統(tǒng)優(yōu)化運(yùn)行與節(jié)能控制需求的問(wèn)題，本文利用支持向量回歸機(jī)的強(qiáng)大非線性映射能力，分別對(duì)小規(guī)模訓(xùn)練樣本和大規(guī)模訓(xùn)練樣本條件下空調(diào)負(fù)荷預(yù)測(cè)支持向量回歸機(jī)模型的在線建模、在線預(yù)測(cè)算法等方面展開(kāi)了研究。論文的主要研究工作包括： （1）針對(duì)基于SVR的空調(diào)負(fù)荷預(yù)測(cè)模型參數(shù)難以確定及計(jì)算量過(guò)大的問(wèn)題，本文提出了基于粒子群的空調(diào)負(fù)荷預(yù)測(cè)SVR模型參數(shù)優(yōu)化算法，并建立了SVR空調(diào)負(fù)荷預(yù)測(cè)模型。仿真結(jié)果表明，本文提出的粒子群優(yōu)化算法與網(wǎng)格搜索法、遺傳算法比較，具有更快的尋優(yōu)時(shí)間，，尋優(yōu)時(shí)間僅為網(wǎng)格搜索法的7.1%~22.7%，遺傳算法的22.8%~55.5%，該方法大幅度地縮短了空調(diào)負(fù)荷預(yù)測(cè)模型參數(shù)尋優(yōu)時(shí)間，為空調(diào)負(fù)荷SVR預(yù)測(cè)模型提供了有效的參數(shù)優(yōu)化算法。 （2）針對(duì)常規(guī)離線SVR預(yù)測(cè)模型需要對(duì)模型進(jìn)行重新訓(xùn)練，效率較差的問(wèn)題，本文提出了小規(guī)模訓(xùn)練樣本條件下建筑物空調(diào)負(fù)荷Online SVR預(yù)測(cè)算法。仿真結(jié)果表明，Online SVR預(yù)測(cè)模型在較小訓(xùn)練樣本集下具有更優(yōu)越的預(yù)測(cè)性能，但是，Online SVR預(yù)測(cè)模型受輸入?yún)?shù)的影響較大。 （3）針對(duì)當(dāng)前空調(diào)負(fù)荷預(yù)測(cè)影響因素“時(shí)變”導(dǎo)致空調(diào)負(fù)荷預(yù)測(cè)模型不準(zhǔn)確，影響負(fù)荷預(yù)測(cè)精度的問(wèn)題，本文提出了大規(guī)模訓(xùn)練樣本條件下基于SVR的空調(diào)負(fù)荷滾動(dòng)預(yù)測(cè)算法，建立了SVR滾動(dòng)預(yù)測(cè)模型。此外，算法利用當(dāng)日前一小時(shí)的滾動(dòng)信息，不斷對(duì)模型進(jìn)行修正以提高負(fù)荷預(yù)測(cè)精度。論文同時(shí)探討了以期望誤差百分比（EEP）為預(yù)測(cè)評(píng)價(jià)指標(biāo)時(shí)，不同訓(xùn)練樣本長(zhǎng)度對(duì)神經(jīng)網(wǎng)絡(luò)和SVR算法預(yù)測(cè)精度的影響。預(yù)測(cè)結(jié)果表明，基于SVR的空調(diào)負(fù)荷滾動(dòng)預(yù)測(cè)算法較常規(guī)SVR預(yù)測(cè)算法和神經(jīng)網(wǎng)絡(luò)預(yù)測(cè)算法預(yù)測(cè)精度分別提高了20.1%和19.8%，當(dāng)訓(xùn)練樣本較少時(shí)，本文提出的SVR滾動(dòng)預(yù)測(cè)算法預(yù)測(cè)性能更為優(yōu)越。
[Abstract]:To improve the accuracy of air conditioning load forecasting is the basis and prerequisite to realize energy saving operation and optimal control of air conditioning system. Aiming at the problem that the accuracy and speed of the existing load forecasting algorithms are difficult to meet the requirements of optimal operation and energy-saving control of air conditioning system, the powerful nonlinear mapping ability of support vector regression machine is used in this paper. The on-line modeling and on-line prediction algorithm of support vector regression model for air conditioning load forecasting under the condition of small scale training samples and large scale training samples are studied respectively. The main work of this paper is as follows: (1) aiming at the problem that the parameters of air conditioning load forecasting model based on SVR are difficult to determine and the amount of calculation is too large, a particle swarm optimization algorithm for air conditioning load forecasting SVR model parameter optimization is proposed in this paper. The load forecasting model of SVR air conditioning is established. The simulation results show that the particle swarm optimization algorithm proposed in this paper has faster searching time than the grid search algorithm and genetic algorithm. The optimization time is only 7.1and 22.722.7in the grid search method, while the genetic algorithm is 22.85.5. this method greatly shortens the optimization time of the air conditioning load forecasting model parameters, and provides an effective parameter optimization algorithm for the air conditioning load SVR forecasting model. (2) aiming at the problem that the conventional off-line SVR forecasting model needs to be retrained and its efficiency is poor, this paper proposes a Online SVR forecasting algorithm for building air conditioning load under the condition of small-scale training samples. The simulation results show that the online SVR prediction model has better prediction performance under the small training sample set, but the online SVR prediction model is greatly affected by the input parameters. (3) aiming at the problem that the influence factor of air conditioning load forecasting is "time-varying", which results in the inaccurate air conditioning load forecasting model and affecting the precision of load forecasting, this paper proposes a rolling forecasting algorithm for air conditioning load based on SVR under the condition of large-scale training sample. The rolling prediction model of SVR is established. In addition, the algorithm makes use of the rolling information of the first hour of the day and constantly modifies the model to improve the accuracy of load forecasting. At the same time, the paper discusses the influence of different training sample length on the prediction accuracy of neural network and SVR algorithm when the expected error percentage (EEP) is used as the prediction evaluation index. The prediction results show that the prediction accuracy of the air conditioning load rolling forecasting algorithm based on SVR is improved by 20.1% and 19.8%, respectively, compared with the conventional SVR forecasting algorithm and the neural network forecasting algorithm. The prediction performance of SVR rolling prediction algorithm proposed in this paper is superior.
【學(xué)位授予單位】：華南理工大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2013
【分類(lèi)號(hào)】：TU831

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 冀衛(wèi)興;陳忠海;方箏;;基于DE—BP算法的空調(diào)負(fù)荷預(yù)測(cè)研究[J];四川建筑科學(xué)研究;2010年05期

2 孫靖,程大章;基于季節(jié)性時(shí)間序列模型的空調(diào)負(fù)荷預(yù)測(cè)[J];電工技術(shù)學(xué)報(bào);2004年03期

3 王小純;劉蕾;;基于PSO-BP算法的動(dòng)態(tài)空調(diào)負(fù)荷預(yù)測(cè)建模[J];裝備制造技術(shù);2011年05期

4 余鵬;吳培浩;楊仕超;;廣東省國(guó)家機(jī)關(guān)辦公建筑和大型公共建筑能耗統(tǒng)計(jì)與分析[J];廣東土木與建筑;2012年04期

5 李志生;張國(guó)強(qiáng);李冬梅;梅勝;劉旭紅;李利新;;廣州地區(qū)大型辦公類(lèi)公共建筑能耗調(diào)查與分析[J];重慶建筑大學(xué)學(xué)報(bào);2008年05期

6 田翔,鄧飛其;精確在線支持向量回歸在股指預(yù)測(cè)中的應(yīng)用[J];計(jì)算機(jī)工程;2005年22期

7 李海軍;何大四;;泛化能力改善的神經(jīng)網(wǎng)絡(luò)方法在空調(diào)負(fù)荷預(yù)測(cè)中的應(yīng)用[J];建筑科學(xué);2009年06期

8 常曉珂,夏Q

本文編號(hào)：2255728