【摘要】：為了提高建筑空調(diào)負(fù)荷的預(yù)測(cè)精度,在分析空調(diào)負(fù)荷主要影響因素的基礎(chǔ)上提出了一種基于自適應(yīng)加權(quán)最小二乘支持向量機(jī)(AWLS-SVM)的建筑空調(diào)負(fù)荷預(yù)測(cè)方法。該方法根據(jù)預(yù)測(cè)誤差的統(tǒng)計(jì)特性,采用基于改進(jìn)正態(tài)分布加權(quán)規(guī)則,自適應(yīng)地賦予每個(gè)建模樣本不同的權(quán)值,以克服異常樣本點(diǎn)對(duì)模型性能的影響。建模過程中采用粒子群優(yōu)化(PSO)算法對(duì)模型參數(shù)進(jìn)行優(yōu)化,以進(jìn)一步提高模型預(yù)測(cè)精度。基于DeST模擬數(shù)據(jù)將AWLS-SVM方法應(yīng)用于南方地區(qū)某辦公建筑的逐時(shí)空調(diào)負(fù)荷預(yù)測(cè)中,并與徑向基神經(jīng)網(wǎng)絡(luò)(RBFNN)模型、LS-SVM模型及WLS-SVM模型作比較,其平均預(yù)測(cè)絕對(duì)誤差分別降低了51.84%、13.95%和3.24%,并進(jìn)一步基于實(shí)際空調(diào)負(fù)荷數(shù)據(jù)將該方法應(yīng)用于另一辦公建筑的逐日空調(diào)負(fù)荷預(yù)測(cè)中。預(yù)測(cè)結(jié)果表明:AWLS-SVM預(yù)測(cè)的累積負(fù)荷誤差為4.56MW,亦優(yōu)于其他3類模型,證明了AWLS-SVM具有較高的預(yù)測(cè)精度和較好的泛化能力,是建筑空調(diào)負(fù)荷預(yù)測(cè)的一種有效方法。
[Abstract]:In order to improve the precision of building air conditioning load prediction, an adaptive weighted least square support vector machine (AWLS-SVM) based building air conditioning load forecasting method is proposed based on the analysis of the main factors affecting the air conditioning load. According to the statistical characteristics of prediction error, the method adaptively assigns different weights to each modeling sample based on the improved normal distribution weighting rule, in order to overcome the influence of abnormal sample points on the performance of the model. In the process of modeling, particle swarm optimization (PSO) algorithm is used to optimize the model parameters to further improve the prediction accuracy of the model. Based on the DeST simulation data, the AWLS-SVM method is applied to the hourly air conditioning load forecasting of an office building in southern China. The results are compared with the radial basis function neural network (RBF) (RBFNN) model, LS-SVM model and WLS-SVM model. The average absolute error of prediction is reduced by 51.84% and 3.24%, respectively. The method is further applied to the daily air conditioning load forecasting of another office building based on the actual air conditioning load data. The prediction results show that the cumulative load error of AWLS-SVM is 4.56MW, which is better than other three models. It is proved that AWLS-SVM has higher prediction accuracy and better generalization ability, and it is an effective method for building air conditioning load forecasting.
【作者單位】： 福州大學(xué)石油化工學(xué)院;
【基金】：國(guó)家自然科學(xué)基金資助項(xiàng)目(6080402,61374133) 高校博士點(diǎn)專項(xiàng)科研基金(20133314120004)~~
【分類號(hào)】：TU831.1;TP18

【相似文獻(xiàn)】

相關(guān)期刊論文 前10條

1 鐘慶,吳捷,鐘丹虹;基于系統(tǒng)論的負(fù)荷預(yù)測(cè)集成化方法[J];電力自動(dòng)化設(shè)備;2002年10期

2 張伏生,劉芳,趙文彬,寇強(qiáng),劉沛津,曹正建;基于Internet/Intranet的負(fù)荷預(yù)測(cè)系統(tǒng)方案[J];電力系統(tǒng)自動(dòng)化;2003年10期

3 康重慶;牟濤;夏清;;電力系統(tǒng)多級(jí)負(fù)荷預(yù)測(cè)及其協(xié)調(diào)問題 (一)研究框架[J];電力系統(tǒng)自動(dòng)化;2008年07期

4 李小銳;黎燦兵;袁彥;;基于下級(jí)負(fù)荷預(yù)測(cè)的短期負(fù)荷預(yù)測(cè)新算法[J];江西電力職業(yè)技術(shù)學(xué)院學(xué)報(bào);2008年02期

5 李新煒;王子琦;方鳴;周鵬;王啟明;李同;鞠平;;基于分區(qū)逐時(shí)氣象信息的全網(wǎng)負(fù)荷預(yù)測(cè)研究[J];電力系統(tǒng)保護(hù)與控制;2009年03期

6 康重慶;趙燃;陳新宇;楊興宇;曹欣;劉梅;;多級(jí)負(fù)荷預(yù)測(cè)的基礎(chǔ)問題分析[J];電力系統(tǒng)保護(hù)與控制;2009年09期

7 任峰;丁超;;市場(chǎng)環(huán)境下負(fù)荷預(yù)測(cè)誤差風(fēng)險(xiǎn)管理研究[J];現(xiàn)代電力;2009年03期

8 羅鳳章;王成山;肖峻;侯磊;王建民;李亦農(nóng);陳春琴;王賽一;;計(jì)及氣溫因素的年度負(fù)荷預(yù)測(cè)修正方法[J];電力系統(tǒng)及其自動(dòng)化學(xué)報(bào);2009年03期

9 楊凱;;如何提高負(fù)荷預(yù)測(cè)的準(zhǔn)確率[J];大眾用電;2009年10期

10 李q，

本文編號(hào)：2282912