schliessen

Filtern

 

Bibliotheken

Combined Forecasting for Short-Term Output Power of Wind Farm

Wind power forecast is of great significance for power grid operation and scheduling. The effection of historical time series of output power and weather factors to wind power are considered in this paper. By use of BP neural network, an iterative forecasting model about output power time series is... Full description

Journal Title: Advanced Materials Research 2012, Vol.347, pp.3551-3554
Main Author: Wang, Xiao Lan
Other Authors: Chen, Qian Cheng
Format: Electronic Article Electronic Article
Language: English
ID: ISSN: 1022-6680 ; E-ISSN: 1662-8985 ; DOI: 10.4028/www.scientific.net/AMR.347-353.3551
Link: http://www.scientific.net/AMR.347-353.3551
Zum Text:
SendSend as email Add to Book BagAdd to Book Bag
Staff View
recordid: transtech10.4028/www.scientific.net/AMR.347-353.3551
title: Combined Forecasting for Short-Term Output Power of Wind Farm
format: Article
creator:
  • Wang, Xiao Lan
  • Chen, Qian Cheng
ispartof: Advanced Materials Research, 2012, Vol.347, pp.3551-3554
description: Wind power forecast is of great significance for power grid operation and scheduling. The effection of historical time series of output power and weather factors to wind power are considered in this paper. By use of BP neural network, an iterative forecasting model about output power time series is built. An Elman neural network forecasting model is established between numerical weather prediction data and output power. Then combining the above two forecasting models using covariance optimal combination method, a combined forecasting model for wind power is achieved so as to use all effective information of different data. The simulation experiment shows that the prediction accuracy has been improved by the combination forecast.
language: eng
source:
identifier: ISSN: 1022-6680 ; E-ISSN: 1662-8985 ; DOI: 10.4028/www.scientific.net/AMR.347-353.3551
fulltext: fulltext
issn:
  • 1022-6680
  • 1662-8985
  • 10226680
  • 16628985
url: Link


@attributes
ID988574103
RANK0.07
NO1
SEARCH_ENGINEprimo_central_multiple_fe
SEARCH_ENGINE_TYPEPrimo Central Search Engine
LOCALfalse
PrimoNMBib
record
control
sourcerecordid10.4028/www.scientific.net/AMR.347-353.3551
sourceidtranstech
recordidTN_transtech10.4028/www.scientific.net/AMR.347-353.3551
sourcesystemPC
display
typearticle
titleCombined Forecasting for Short-Term Output Power of Wind Farm
creatorWang, Xiao Lan ; Chen, Qian Cheng
ispartofAdvanced Materials Research, 2012, Vol.347, pp.3551-3554
identifier
descriptionWind power forecast is of great significance for power grid operation and scheduling. The effection of historical time series of output power and weather factors to wind power are considered in this paper. By use of BP neural network, an iterative forecasting model about output power time series is built. An Elman neural network forecasting model is established between numerical weather prediction data and output power. Then combining the above two forecasting models using covariance optimal combination method, a combined forecasting model for wind power is achieved so as to use all effective information of different data. The simulation experiment shows that the prediction accuracy has been improved by the combination forecast.
languageeng
source
version2
lds50peer_reviewed
links
openurl$$Topenurl_article
backlink$$Uhttp://www.scientific.net/AMR.347-353.3551$$DView this record in Scientific.Net (Trans Tech Publications)
openurlfulltext$$Topenurlfull_article
search
creatorcontrib
0Wang, Xiao Lan
1Chen, Qian Cheng
titleCombined Forecasting for Short-Term Output Power of Wind Farm
descriptionWind power forecast is of great significance for power grid operation and scheduling. The effection of historical time series of output power and weather factors to wind power are considered in this paper. By use of BP neural network, an iterative forecasting model about output power time series is built. An Elman neural network forecasting model is established between numerical weather prediction data and output power. Then combining the above two forecasting models using covariance optimal combination method, a combined forecasting model for wind power is achieved so as to use all effective information of different data. The simulation experiment shows that the prediction accuracy has been improved by the combination forecast.
general
010.4028/www.scientific.net/AMR.347-353.3551
1eng
2Scientific.Net (Trans Tech Publications)
sourceidtranstech
recordidtranstech10.4028/www.scientific.net/AMR.347-353.3551
issn
01022-6680
11662-8985
210226680
316628985
rsrctypearticle
creationdate2012
recordtypearticle
addtitleAdvanced Materials Research
searchscopetranstech
scopetranstech
lsr30VSR-Enriched:[pages, isbn]
sort
titleCombined Forecasting for Short-Term Output Power of Wind Farm
authorWang, Xiao Lan ; Chen, Qian Cheng
creationdate20120109
facets
frbrgroupid-7747724358048157919
frbrtype5
languageeng
creationdate2012
collectionScientific.Net (Trans Tech Publications)
prefilterarticles
rsrctypearticles
creatorcontrib
0Wang, Xiao Lan
1Chen, Qian Cheng
jtitleAdvanced Materials Research
toplevelpeer_reviewed
delivery
delcategoryRemote Search Resource
fulltextfulltext
addata
aulast
0Wang
1Chen
aufirst
0Xiao Lan
1Qian Cheng
au
0Wang, Xiao Lan
1Chen, Qian Cheng
atitleCombined Forecasting for Short-Term Output Power of Wind Farm
jtitleAdvanced Materials Research
risdate20120109
volume347
spage3551
epage3554
issn1022-6680
eissn1662-8985
genrearticle
ristypeJOUR
abstractWind power forecast is of great significance for power grid operation and scheduling. The effection of historical time series of output power and weather factors to wind power are considered in this paper. By use of BP neural network, an iterative forecasting model about output power time series is built. An Elman neural network forecasting model is established between numerical weather prediction data and output power. Then combining the above two forecasting models using covariance optimal combination method, a combined forecasting model for wind power is achieved so as to use all effective information of different data. The simulation experiment shows that the prediction accuracy has been improved by the combination forecast.
pubTrans Tech Publications
doi10.4028/www.scientific.net/AMR.347-353.3551
pages3551-3554
isbn9783037852651
date2012-01-09