Assessing stacked physics-informed machine learning models for co-located wind–solar power forecasting

TY - JOUR

T1 - Assessing stacked physics-informed machine learning models for co-located wind–solar power forecasting

AU - Pombo, Daniel Vázquez

AU - Rincón, Mario Javier

AU - Bacher, Peder

AU - Bindner, Henrik W.

AU - Spataru, Sergiu V.

AU - Sørensen, Poul E.

N1 - Publisher Copyright: © 2022 The Author(s)

PY - 2022/12

Y1 - 2022/12

N2 - Increasingly advanced stochastic energy management systems are employed to facilitate the integration of wind and solar PV in worldwide power grids. In this context, forecasting is a key tool limiting the success of said control actions. This paper explores the suitability of stacked machine learning based models to predict wind and solar power available in the same site using a physics informed approach. The method recombines basic meteorological metrics widely available to compute new physics informed ones facilitating the learning procedure, while other are weak ML-models themselves. Further, to facilitate the integration of the point forecasters in the stochastic optimization field, we propose a simple unsupervised estimation of the error distribution. In this way, scenarios can be easily and homogeneously characterized for different resolutions and horizons. A study case is presented employing the Open Access dataset SOLETE, to facilitate benchmarking and replication of results. The results show accuracy improvements over the previously reported work over the same dataset.

AB - Increasingly advanced stochastic energy management systems are employed to facilitate the integration of wind and solar PV in worldwide power grids. In this context, forecasting is a key tool limiting the success of said control actions. This paper explores the suitability of stacked machine learning based models to predict wind and solar power available in the same site using a physics informed approach. The method recombines basic meteorological metrics widely available to compute new physics informed ones facilitating the learning procedure, while other are weak ML-models themselves. Further, to facilitate the integration of the point forecasters in the stochastic optimization field, we propose a simple unsupervised estimation of the error distribution. In this way, scenarios can be easily and homogeneously characterized for different resolutions and horizons. A study case is presented employing the Open Access dataset SOLETE, to facilitate benchmarking and replication of results. The results show accuracy improvements over the previously reported work over the same dataset.

KW - Co-located wind and solar

KW - Hybrid

KW - Machine learning

KW - Microgrid

KW - Stochastic optimization

UR - https://www.scopus.com/pages/publications/85140629800

U2 - 10.1016/j.segan.2022.100943

DO - 10.1016/j.segan.2022.100943

M3 - Journal article

AN - SCOPUS:85140629800

SN - 2352-4677

VL - 32

JO - Sustainable Energy, Grids and Networks

JF - Sustainable Energy, Grids and Networks

M1 - 100943

ER -