Short-term spatio-temporal prediction of wind speed and direction

Research output: Contribution to journalArticle

21 Citations (Scopus)

Abstract

This paper aims to produce a low-complexity predictor for the hourly mean wind speed and direction from 1 to 6 h ahead at multiple sites distributed around the UK. The wind speed and direction are modelled via the magnitude and phase of a complex-valued time series. A multichannel adaptive filter is set to predict this signal on the basis of its past values and the spatio-temporal correlation between wind signals measured at numerous geographical locations. The filter coefficients are determined by minimizing the mean square prediction error. To account for the time-varying nature of the wind data and the underlying system, we propose a cyclo-stationary Wiener solution, which is shown to produce an accurate predictor. An iterative solution, which provides lower computational complexity, increased robustness towards ill-conditioning of the data covariance matrices and the ability to track time-variations in the underlying system, is also presented. The approaches are tested on wind speed and direction data measured at various sites across the UK. Results show that the proposed techniques are able to predict wind speed as accurately as state-of-the-art wind speed forecasting benchmarks while simultaneously providing valuable directional information.
LanguageEnglish
Pages1945-1955
Number of pages11
JournalWind Energy
Volume17
Issue number12
Early online date20 Oct 2013
DOIs
Publication statusPublished - 1 Dec 2014

Fingerprint

Adaptive filters
Covariance matrix
Time series
Computational complexity

Keywords

  • spatio-temporal prediction
  • wind forecasting
  • multichannel adaptive filter
  • wiener filter

Cite this

@article{3a3fc8e90d724a8dba5dae9da0c50790,
title = "Short-term spatio-temporal prediction of wind speed and direction",
abstract = "This paper aims to produce a low-complexity predictor for the hourly mean wind speed and direction from 1 to 6 h ahead at multiple sites distributed around the UK. The wind speed and direction are modelled via the magnitude and phase of a complex-valued time series. A multichannel adaptive filter is set to predict this signal on the basis of its past values and the spatio-temporal correlation between wind signals measured at numerous geographical locations. The filter coefficients are determined by minimizing the mean square prediction error. To account for the time-varying nature of the wind data and the underlying system, we propose a cyclo-stationary Wiener solution, which is shown to produce an accurate predictor. An iterative solution, which provides lower computational complexity, increased robustness towards ill-conditioning of the data covariance matrices and the ability to track time-variations in the underlying system, is also presented. The approaches are tested on wind speed and direction data measured at various sites across the UK. Results show that the proposed techniques are able to predict wind speed as accurately as state-of-the-art wind speed forecasting benchmarks while simultaneously providing valuable directional information.",
keywords = "spatio-temporal prediction, wind forecasting, multichannel adaptive filter, wiener filter",
author = "Jethro Dowell and Stephan Weiss and David Hill and David Infield",
year = "2014",
month = "12",
day = "1",
doi = "10.1002/we.1682",
language = "English",
volume = "17",
pages = "1945--1955",
journal = "Wind Energy",
issn = "1095-4244",
number = "12",

}

Short-term spatio-temporal prediction of wind speed and direction. / Dowell, Jethro; Weiss, Stephan; Hill, David; Infield, David.

In: Wind Energy, Vol. 17, No. 12, 01.12.2014, p. 1945-1955.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Short-term spatio-temporal prediction of wind speed and direction

AU - Dowell, Jethro

AU - Weiss, Stephan

AU - Hill, David

AU - Infield, David

PY - 2014/12/1

Y1 - 2014/12/1

N2 - This paper aims to produce a low-complexity predictor for the hourly mean wind speed and direction from 1 to 6 h ahead at multiple sites distributed around the UK. The wind speed and direction are modelled via the magnitude and phase of a complex-valued time series. A multichannel adaptive filter is set to predict this signal on the basis of its past values and the spatio-temporal correlation between wind signals measured at numerous geographical locations. The filter coefficients are determined by minimizing the mean square prediction error. To account for the time-varying nature of the wind data and the underlying system, we propose a cyclo-stationary Wiener solution, which is shown to produce an accurate predictor. An iterative solution, which provides lower computational complexity, increased robustness towards ill-conditioning of the data covariance matrices and the ability to track time-variations in the underlying system, is also presented. The approaches are tested on wind speed and direction data measured at various sites across the UK. Results show that the proposed techniques are able to predict wind speed as accurately as state-of-the-art wind speed forecasting benchmarks while simultaneously providing valuable directional information.

AB - This paper aims to produce a low-complexity predictor for the hourly mean wind speed and direction from 1 to 6 h ahead at multiple sites distributed around the UK. The wind speed and direction are modelled via the magnitude and phase of a complex-valued time series. A multichannel adaptive filter is set to predict this signal on the basis of its past values and the spatio-temporal correlation between wind signals measured at numerous geographical locations. The filter coefficients are determined by minimizing the mean square prediction error. To account for the time-varying nature of the wind data and the underlying system, we propose a cyclo-stationary Wiener solution, which is shown to produce an accurate predictor. An iterative solution, which provides lower computational complexity, increased robustness towards ill-conditioning of the data covariance matrices and the ability to track time-variations in the underlying system, is also presented. The approaches are tested on wind speed and direction data measured at various sites across the UK. Results show that the proposed techniques are able to predict wind speed as accurately as state-of-the-art wind speed forecasting benchmarks while simultaneously providing valuable directional information.

KW - spatio-temporal prediction

KW - wind forecasting

KW - multichannel adaptive filter

KW - wiener filter

UR - http://onlinelibrary.wiley.com/journal/10.1002/%28ISSN%291099-1824

U2 - 10.1002/we.1682

DO - 10.1002/we.1682

M3 - Article

VL - 17

SP - 1945

EP - 1955

JO - Wind Energy

T2 - Wind Energy

JF - Wind Energy

SN - 1095-4244

IS - 12

ER -