Short-term forecasting of wind speed and direction exploiting data non-stationarity

Research output: Chapter in Book/Report/Conference proceedingConference contribution book

Abstract

This paper explores how the accuracy of short-term prediction of wind speed and direction can be enhanced by considering the diurnal variation of the wind. The wind speed and direction are modelled as the magnitude and phase of a complex-valued time series. The prediction is performed by a multichannel filter using the spatio-temporal correlation between measurements at different geographical locations and the past values of the target site. A multichannel complex-valued non-stationary prediction Wiener filter is proposed that takes into account both the seasonal and diurnal variation of the wind. Using hourly wind speed and direction measurements from over 22 Met Office weather stations distributed across the UK, we demonstrate that there can be a benefit for predicting one hour ahead when taking into account the diurnal and seasonal cyclo-stationary nature of the wind.
LanguageEnglish
Title of host publicationInternational Work-Conference on Time Series
PublisherSpringer-Verlag
Pages1-12
Number of pages12
Publication statusAccepted/In press - 28 Apr 2015

Fingerprint

Time series

Keywords

  • multichannel predictive filter
  • non-stationarity
  • short-term wind forecast

Cite this

Malvaldi, A., Dowell, J., Weiss, S., & Infield, D. (Accepted/In press). Short-term forecasting of wind speed and direction exploiting data non-stationarity. In International Work-Conference on Time Series (pp. 1-12). Springer-Verlag.
@inproceedings{d49bbc7d166a4183ab0ef0db2be22eb6,
title = "Short-term forecasting of wind speed and direction exploiting data non-stationarity",
abstract = "This paper explores how the accuracy of short-term prediction of wind speed and direction can be enhanced by considering the diurnal variation of the wind. The wind speed and direction are modelled as the magnitude and phase of a complex-valued time series. The prediction is performed by a multichannel filter using the spatio-temporal correlation between measurements at different geographical locations and the past values of the target site. A multichannel complex-valued non-stationary prediction Wiener filter is proposed that takes into account both the seasonal and diurnal variation of the wind. Using hourly wind speed and direction measurements from over 22 Met Office weather stations distributed across the UK, we demonstrate that there can be a benefit for predicting one hour ahead when taking into account the diurnal and seasonal cyclo-stationary nature of the wind.",
keywords = "multichannel predictive filter, non-stationarity, short-term wind forecast",
author = "Alice Malvaldi and Jethro Dowell and Stephan Weiss and David Infield",
year = "2015",
month = "4",
day = "28",
language = "English",
pages = "1--12",
booktitle = "International Work-Conference on Time Series",
publisher = "Springer-Verlag",

}

Short-term forecasting of wind speed and direction exploiting data non-stationarity. / Malvaldi, Alice; Dowell, Jethro; Weiss, Stephan; Infield, David.

International Work-Conference on Time Series. Springer-Verlag, 2015. p. 1-12.

Research output: Chapter in Book/Report/Conference proceedingConference contribution book

TY - GEN

T1 - Short-term forecasting of wind speed and direction exploiting data non-stationarity

AU - Malvaldi, Alice

AU - Dowell, Jethro

AU - Weiss, Stephan

AU - Infield, David

PY - 2015/4/28

Y1 - 2015/4/28

N2 - This paper explores how the accuracy of short-term prediction of wind speed and direction can be enhanced by considering the diurnal variation of the wind. The wind speed and direction are modelled as the magnitude and phase of a complex-valued time series. The prediction is performed by a multichannel filter using the spatio-temporal correlation between measurements at different geographical locations and the past values of the target site. A multichannel complex-valued non-stationary prediction Wiener filter is proposed that takes into account both the seasonal and diurnal variation of the wind. Using hourly wind speed and direction measurements from over 22 Met Office weather stations distributed across the UK, we demonstrate that there can be a benefit for predicting one hour ahead when taking into account the diurnal and seasonal cyclo-stationary nature of the wind.

AB - This paper explores how the accuracy of short-term prediction of wind speed and direction can be enhanced by considering the diurnal variation of the wind. The wind speed and direction are modelled as the magnitude and phase of a complex-valued time series. The prediction is performed by a multichannel filter using the spatio-temporal correlation between measurements at different geographical locations and the past values of the target site. A multichannel complex-valued non-stationary prediction Wiener filter is proposed that takes into account both the seasonal and diurnal variation of the wind. Using hourly wind speed and direction measurements from over 22 Met Office weather stations distributed across the UK, we demonstrate that there can be a benefit for predicting one hour ahead when taking into account the diurnal and seasonal cyclo-stationary nature of the wind.

KW - multichannel predictive filter

KW - non-stationarity

KW - short-term wind forecast

UR - http://itise.ugr.es/

M3 - Conference contribution book

SP - 1

EP - 12

BT - International Work-Conference on Time Series

PB - Springer-Verlag

ER -

Malvaldi A, Dowell J, Weiss S, Infield D. Short-term forecasting of wind speed and direction exploiting data non-stationarity. In International Work-Conference on Time Series. Springer-Verlag. 2015. p. 1-12