Spatio-temporal prediction of wind speed and direction by continuous directional regime

Research output: Contribution to conferencePaper

4 Citations (Scopus)

Abstract

This paper proposes a statistical method for 1-6 hour-ahead prediction of hourly mean wind speed and direction to better forecast the power produced by wind turbines, an increasingly important component of power system operation. The wind speed and direction are modelled via the magnitude and phase of a complex vector containing measurements from multiple geographic locations. The predictor is derived from the spatio-temporal covariance which is estimated at regular time intervals from a subset of the available training data, the wind direction of which lies within a sliding range of angles centred on the most recent measurement of wind direction. This is a generalisation of regime-switching type approaches which train separate predictors for a few fixed regimes. The new predictor is tested on the Hydra dataset of wind across the Netherlands and compared to persistence and a cyclo-stationary Wiener filter, a state-of-the-art spatial predictor of wind speed and direction. Results show that the proposed technique is able to predict the wind vector more accurately than these benchmarks on dataset containing 4 to 27 sites, with greater accuracy for larger datasets.

Conference

Conference2014 International Conference on Probabilistic Methods Applied to Power Systems, PMAPS 2014
Abbreviated titlePMAPS 2014
CountryUnited Kingdom
CityDurham
Period7/07/1410/07/14
Internet address

Fingerprint

Wind turbines
Statistical methods

Keywords

  • load forecasting
  • spatiotemporal phenomena
  • wind turbines
  • complex vector phase
  • power system operation

Cite this

Dowell, J., Weiss, S., & Infield, D. (2014). Spatio-temporal prediction of wind speed and direction by continuous directional regime. 1-5. Paper presented at 2014 International Conference on Probabilistic Methods Applied to Power Systems, PMAPS 2014, Durham, United Kingdom. https://doi.org/10.1109/PMAPS.2014.6960596
Dowell, Jethro ; Weiss, Stephan ; Infield, David. / Spatio-temporal prediction of wind speed and direction by continuous directional regime. Paper presented at 2014 International Conference on Probabilistic Methods Applied to Power Systems, PMAPS 2014, Durham, United Kingdom.5 p.
@conference{2482baa6d2ee4179905367f5b77de766,
title = "Spatio-temporal prediction of wind speed and direction by continuous directional regime",
abstract = "This paper proposes a statistical method for 1-6 hour-ahead prediction of hourly mean wind speed and direction to better forecast the power produced by wind turbines, an increasingly important component of power system operation. The wind speed and direction are modelled via the magnitude and phase of a complex vector containing measurements from multiple geographic locations. The predictor is derived from the spatio-temporal covariance which is estimated at regular time intervals from a subset of the available training data, the wind direction of which lies within a sliding range of angles centred on the most recent measurement of wind direction. This is a generalisation of regime-switching type approaches which train separate predictors for a few fixed regimes. The new predictor is tested on the Hydra dataset of wind across the Netherlands and compared to persistence and a cyclo-stationary Wiener filter, a state-of-the-art spatial predictor of wind speed and direction. Results show that the proposed technique is able to predict the wind vector more accurately than these benchmarks on dataset containing 4 to 27 sites, with greater accuracy for larger datasets.",
keywords = "load forecasting, spatiotemporal phenomena, wind turbines, complex vector phase, power system operation",
author = "Jethro Dowell and Stephan Weiss and David Infield",
year = "2014",
month = "7",
doi = "10.1109/PMAPS.2014.6960596",
language = "English",
pages = "1--5",
note = "2014 International Conference on Probabilistic Methods Applied to Power Systems, PMAPS 2014, PMAPS 2014 ; Conference date: 07-07-2014 Through 10-07-2014",
url = "https://www.dur.ac.uk/dei/events/pmaps2014/",

}

Dowell, J, Weiss, S & Infield, D 2014, 'Spatio-temporal prediction of wind speed and direction by continuous directional regime' Paper presented at 2014 International Conference on Probabilistic Methods Applied to Power Systems, PMAPS 2014, Durham, United Kingdom, 7/07/14 - 10/07/14, pp. 1-5. https://doi.org/10.1109/PMAPS.2014.6960596

Spatio-temporal prediction of wind speed and direction by continuous directional regime. / Dowell, Jethro; Weiss, Stephan; Infield, David.

2014. 1-5 Paper presented at 2014 International Conference on Probabilistic Methods Applied to Power Systems, PMAPS 2014, Durham, United Kingdom.

Research output: Contribution to conferencePaper

TY - CONF

T1 - Spatio-temporal prediction of wind speed and direction by continuous directional regime

AU - Dowell, Jethro

AU - Weiss, Stephan

AU - Infield, David

PY - 2014/7

Y1 - 2014/7

N2 - This paper proposes a statistical method for 1-6 hour-ahead prediction of hourly mean wind speed and direction to better forecast the power produced by wind turbines, an increasingly important component of power system operation. The wind speed and direction are modelled via the magnitude and phase of a complex vector containing measurements from multiple geographic locations. The predictor is derived from the spatio-temporal covariance which is estimated at regular time intervals from a subset of the available training data, the wind direction of which lies within a sliding range of angles centred on the most recent measurement of wind direction. This is a generalisation of regime-switching type approaches which train separate predictors for a few fixed regimes. The new predictor is tested on the Hydra dataset of wind across the Netherlands and compared to persistence and a cyclo-stationary Wiener filter, a state-of-the-art spatial predictor of wind speed and direction. Results show that the proposed technique is able to predict the wind vector more accurately than these benchmarks on dataset containing 4 to 27 sites, with greater accuracy for larger datasets.

AB - This paper proposes a statistical method for 1-6 hour-ahead prediction of hourly mean wind speed and direction to better forecast the power produced by wind turbines, an increasingly important component of power system operation. The wind speed and direction are modelled via the magnitude and phase of a complex vector containing measurements from multiple geographic locations. The predictor is derived from the spatio-temporal covariance which is estimated at regular time intervals from a subset of the available training data, the wind direction of which lies within a sliding range of angles centred on the most recent measurement of wind direction. This is a generalisation of regime-switching type approaches which train separate predictors for a few fixed regimes. The new predictor is tested on the Hydra dataset of wind across the Netherlands and compared to persistence and a cyclo-stationary Wiener filter, a state-of-the-art spatial predictor of wind speed and direction. Results show that the proposed technique is able to predict the wind vector more accurately than these benchmarks on dataset containing 4 to 27 sites, with greater accuracy for larger datasets.

KW - load forecasting

KW - spatiotemporal phenomena

KW - wind turbines

KW - complex vector phase

KW - power system operation

UR - http://ieeexplore.ieee.org/xpl/articleDetails.jsp?tp=&arnumber=6960596

U2 - 10.1109/PMAPS.2014.6960596

DO - 10.1109/PMAPS.2014.6960596

M3 - Paper

SP - 1

EP - 5

ER -

Dowell J, Weiss S, Infield D. Spatio-temporal prediction of wind speed and direction by continuous directional regime. 2014. Paper presented at 2014 International Conference on Probabilistic Methods Applied to Power Systems, PMAPS 2014, Durham, United Kingdom. https://doi.org/10.1109/PMAPS.2014.6960596