|
OALib Journal期刊
ISSN: 2333-9721
费用：99美元
|
|
|
|
基于eemd与lssvr的能源消费量多尺度预测――以广东省为例
DOI: 10.13484/j.nmgdxxbzk.20150303, PP. 234-241
Keywords: 能源消费量,多尺度预测,集合经验模态分解,最小二乘支持向量回归,粒子群优化算法
Abstract:
由于能源消费内在的复杂性,传统的单尺度预测方法很难获得理想的预测效果.为提高能源消费量预测精度,提出了基于集合经验模态分解(eemd)与最小二乘支持向量回归(lssvr)的能源消费量多尺度预测模型.首先应用eemd算法将能源消费量环比指数从高频到低频分解成若干结构更简单、变化更平稳、规律性更强、更易于预测的内在模态函数(imf)和一个残差项;其次利用lssvr对各imf和残差项进行预测,并采用粒子群算法(pso)选择最优的模型参数;然后将各分量的预测值直接加总求和重构出能源消费量环比指数的预测序列;最后通过逆环比化处理,获得原始能源消费量的最终预测值.利用该模型对1980-2013年广东省能源消费量进行实证分析,结果表明多尺度预测模型的确能够显著提高预测精度.
| [1] | inglesir.aggregateelectricitydemandinsouthafrica:conditionalforecaststo2030[j].appliedenergy,2010,87(1):197-204.
|
| [2] | 花玲,谢乃明.政策冲击影响下中国能源消费预测分析及控制策略[j].中国管理科学,2014,22(7):18-25.
|
| [3] | wangjz,zhuwj,zhangwy,etal.atrendfixedonfirstlyandseasonaladjustmentmodelcombinedwiththee-svrforshort-termforecastingofelectricitydemand[j].energypolicy,2009,37(11):4901-4909.
|
| [4] | changpc,fancy,linjj.monthlyelectricitydemandforecastingbasedonaweightedevolvingfuzzyneuralnetworkapproach[j].internationaljournalelectricitypowerenergysystem,2011,33(1):17-27.
|
| [5] | leeys,tongli.forecastingnonlineartimeseriesofenergyconsumptionusingahybriddynamicmodel[j].appliedenergy,2012,94:251-256.
|
| [6] | huangne,wuml,quwd,etal.applicationsofhilberthuangtransformtonon-stationaryfinancialtimeseriesanalysis[j].appliedstochasticmodelsinbusinessandindustry,2003,19:245-268.
|
| [7] | zhubz,weiym.carbonpricepredictionwithahybridarimaandleastsquaressupportvectormachinesmethodology[j].omega,2013,41:517-524.
|
| [8] | dieboldfx,marianors.comparingpredictiveaccuracy[j].journalofbusinessandeconomicstatistics,1995,13(3):253-263.
|
| [9] | adompk,bekoew.conditionaldynamicforecastofelectricalenergyconsumptionrequirementsinghanaby2020:acomparisonofardlandpam[j].energy,2012,44:367-380.
|
| [10] | paoht,fuhc,tsengcl.forecastingofco2emissions,energyconsumptionandeconomicgrowthinchinausinganimprovedgreymodel[j].energy,2012,40:400-409.
|
| [11] | gutiérrezr,gutiérrez-sánchezr,nafidia.electricityconsumptioninmorocco:stochasticgompertzdiffusionanalysiswithexogenousfactors[j].appliedenergy,2006,83(10):1139-1151.
|
| [12] | zhusl,wangjz,zhaowg,etal.aseasonalhybridprocedureforelectricitydemandforecastinginchina[j].appliedenergy,2011,88(11):3807-3815.
|
| [13] | tangl,yul,wangs,etal.anovelhybridensemblelearningparadigmfornuclearenergyconsumptionforecasting[j].appliedenergy,2012,93:432-443.
|
| [14] | wuz,huangne.ensembleempiricalmodedecomposition:anoise-assisteddataanalysismethod[j].advancesinadaptivedataanalysis,2009,1(1):1-41.
|
| [15] | 广东省统计局.广东统计年鉴(2014)[m].北京:中国统计出版社,2014.
|
Full-Text
|
|
Contact Us
service@oalib.com QQ:3279437679 
WhatsApp +8615387084133
|
|
