Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Forecasting High-Frequency Spatio-Temporal Wind Power with Dimensionally Reduced Echo State Networks

About

Fast and accurate hourly forecasts of wind speed and power are crucial in quantifying and planning the energy budget in the electric grid. Modeling 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 modeling 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 the 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 two-hour-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.

Huang Huang, Stefano Castruccio, Marc G. Genton• 2021

Related benchmarks

TaskDatasetResultRank
Epidemic ForecastingJapan TB medium-term (test)
SMAPE23.16
30
Long-term forecastingILI (test)
Empirical Coverage0.24
24
Long-term forecastingJapan TB (test)
Empirical Coverage30
24
Long-term forecastingBelgium COVID-19 (test)
Empirical Coverage10
24
Long-term forecastingColombia Dengue (test)
Empirical Coverage38
24
Long-term forecastingHungary Chickenpox (test)
Empirical Coverage16
24
Long-term forecastingChina TB (test)
Empirical Coverage20
16
Short-term forecastingUSA ILI
SMAPE28.71
15
Short-term forecastingBelgium COVID-19
SMAPE62.4
15
Epidemic ForecastingChina TB medium-term (test)
SMAPE15.35
15
Showing 10 of 14 rows

Other info

Follow for update