Forecasting wind speed with recurrent neural networks

Qing Cao, Bradley T. Ewing, Mark Andrew Thompson

Research output: Contribution to journalArticle

82 Citations (Scopus)

Abstract

This research presents a comparative analysis of the wind speed forecasting accuracy of univariate and multivariate ARIMA models with their recurrent neural network counterparts. The analysis utilizes contemporaneous wind speed time histories taken from the same tower location at five different heights above ground level. A unique aspect of the study is the exploitation of information contained in the wind histories for the various heights when producing forecasts of wind speed for the various heights. The findings indicate that multivariate models perform better than univariate models and that the recurrent neural network models outperform the ARIMA models. The results have important implications for a variety of engineering applications and business related operations.

Original languageEnglish (US)
Pages (from-to)148-154
Number of pages7
JournalEuropean Journal of Operational Research
Volume221
Issue number1
DOIs
StatePublished - Aug 16 2012
Externally publishedYes

Fingerprint

Recurrent neural networks
Wind Speed
Recurrent Neural Networks
ARIMA Models
Forecasting
Multivariate Models
Univariate
Engineering Application
Comparative Analysis
Neural Network Model
Exploitation
Forecast
Towers
History
Industry
Model
ARIMA models

Keywords

  • Forecasting
  • Neural networks
  • Time series
  • Wind speed

ASJC Scopus subject areas

  • Computer Science(all)
  • Modeling and Simulation
  • Management Science and Operations Research
  • Information Systems and Management

Cite this

Forecasting wind speed with recurrent neural networks. / Cao, Qing; Ewing, Bradley T.; Thompson, Mark Andrew.

In: European Journal of Operational Research, Vol. 221, No. 1, 16.08.2012, p. 148-154.

Research output: Contribution to journalArticle

@article{590e3052589a47d58668bbb290acf6b3,
title = "Forecasting wind speed with recurrent neural networks",
abstract = "This research presents a comparative analysis of the wind speed forecasting accuracy of univariate and multivariate ARIMA models with their recurrent neural network counterparts. The analysis utilizes contemporaneous wind speed time histories taken from the same tower location at five different heights above ground level. A unique aspect of the study is the exploitation of information contained in the wind histories for the various heights when producing forecasts of wind speed for the various heights. The findings indicate that multivariate models perform better than univariate models and that the recurrent neural network models outperform the ARIMA models. The results have important implications for a variety of engineering applications and business related operations.",
keywords = "Forecasting, Neural networks, Time series, Wind speed",
author = "Qing Cao and Ewing, {Bradley T.} and Thompson, {Mark Andrew}",
year = "2012",
month = "8",
day = "16",
doi = "10.1016/j.ejor.2012.02.042",
language = "English (US)",
volume = "221",
pages = "148--154",
journal = "European Journal of Operational Research",
issn = "0377-2217",
publisher = "Elsevier",
number = "1",

}

TY - JOUR

T1 - Forecasting wind speed with recurrent neural networks

AU - Cao, Qing

AU - Ewing, Bradley T.

AU - Thompson, Mark Andrew

PY - 2012/8/16

Y1 - 2012/8/16

N2 - This research presents a comparative analysis of the wind speed forecasting accuracy of univariate and multivariate ARIMA models with their recurrent neural network counterparts. The analysis utilizes contemporaneous wind speed time histories taken from the same tower location at five different heights above ground level. A unique aspect of the study is the exploitation of information contained in the wind histories for the various heights when producing forecasts of wind speed for the various heights. The findings indicate that multivariate models perform better than univariate models and that the recurrent neural network models outperform the ARIMA models. The results have important implications for a variety of engineering applications and business related operations.

AB - This research presents a comparative analysis of the wind speed forecasting accuracy of univariate and multivariate ARIMA models with their recurrent neural network counterparts. The analysis utilizes contemporaneous wind speed time histories taken from the same tower location at five different heights above ground level. A unique aspect of the study is the exploitation of information contained in the wind histories for the various heights when producing forecasts of wind speed for the various heights. The findings indicate that multivariate models perform better than univariate models and that the recurrent neural network models outperform the ARIMA models. The results have important implications for a variety of engineering applications and business related operations.

KW - Forecasting

KW - Neural networks

KW - Time series

KW - Wind speed

UR - http://www.scopus.com/inward/record.url?scp=84860255082&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84860255082&partnerID=8YFLogxK

U2 - 10.1016/j.ejor.2012.02.042

DO - 10.1016/j.ejor.2012.02.042

M3 - Article

VL - 221

SP - 148

EP - 154

JO - European Journal of Operational Research

JF - European Journal of Operational Research

SN - 0377-2217

IS - 1

ER -