Fast and accurate hourly forecasts of wind speed and power are crucial in quantifying and planning the energy budget in the electric grid. Modelling wind at a high resolution brings forth considerable challenges given its turbulent and highly nonlinear dynamics. In developing countries, where wind farms over a large domain are currently under construction or consideration, this is even more challenging given the necessity of modelling wind over space as well. In this work, we propose a machine learning approach to model the nonlinear hourly wind dynamics in Saudi Arabia with a domain-specific choice of knots to reduce spatial dimensionality. Our results show that for locations highlighted as wind abundant by a previous work, our approach results in an 11% improvement in the 2-h-ahead forecasted power against operational standards in the wind energy sector, yielding a saving of nearly one million US dollars over a year under current market prices in Saudi Arabia.
|Original language||English (US)|
|Journal||Journal of the Royal Statistical Society: Series C (Applied Statistics)|
|State||Published - Jan 23 2022|
Bibliographical noteKAUST Repository Item: Exported on 2022-01-25
Acknowledged KAUST grant number(s): OSR-2018-CRG7-3742.
Acknowledgements: King Abdullah University of Science and Technology (KAUST) Office of Sponsored Research (OSR). Grant Number: OSR-2018-CRG7-3742.
ASJC Scopus subject areas
- Statistics and Probability
- Statistics, Probability and Uncertainty
FingerprintDive into the research topics of 'Forecasting high-frequency spatio-temporal wind power with dimensionally reduced echo state networks'. Together they form a unique fingerprint.
Datasets for "Forecasting High-Frequency Spatio-Temporal Wind Power with Dimensionally ReducedEcho State Networks"
Huang, H. (Creator), Castruccio, S. (Creator), Genton, M. (Creator), Castruccio, S. (Creator) & Castruccio, S. (Creator), KAUST Research Repository, Jan 31 2021
DOI: 10.25781/KAUST-SW314, http://hdl.handle.net/10754/667127