Application-Driven Learning: A Closed-Loop Prediction and Optimization Approach Applied to Dynamic Reserves and Demand Forecasting
Operations Research · 2025-01 · 73 (1) · 22-39
DOI: 10.1287/opre.2023.0565 ↗Kurz gefasst
Fachartikel in der Zeitschrift Operations Research, 2025-01. Verfasst von Joaquim Dias Garcia und 3 weiteren Autor:innen. Die Arbeit wurde bisher 29-mal zitiert (Crossref) und nennt 42 Literaturangaben.
Abstract (Originalsprache)
Application-Driven Learning: Closing the Loop Between the Application and the Estimation of Forecast Models This paper introduces a closed-loop framework called application-driven learning, where the best forecast model is tailored to the application cost structure. Our methodology employs two-stage optimization schemes to derive multivariate point forecasts. The estimation problem is conceived as a bilevel model, and we propose two solution methodologies: an exact one using KKT conditions and a scalable decomposition heuristic. This approach offers a scientifically grounded alternative to ad hoc demand biasing approaches and reserve requirement rules currently adopted by power system operators worldwide. Testing with real data and large-scale systems demonstrates that our methodology consistently outperforms traditional open-loop methods, providing significant potential benefits for energy system operations.
Zitieren
APA
Garcia, J. D., Street, A., Homem-de-Mello, T., & Muñoz, F. D. (2025). Application-Driven Learning: A Closed-Loop Prediction and Optimization Approach Applied to Dynamic Reserves and Demand Forecasting. Operations Research, 73(1), 22-39. https://doi.org/10.1287/opre.2023.0565
Vancouver
Garcia JD, Street A, Homem-de-Mello T, Muñoz FD. Application-Driven Learning: A Closed-Loop Prediction and Optimization Approach Applied to Dynamic Reserves and Demand Forecasting. Operations Research. 2025;73(1):22-39. doi:10.1287/opre.2023.0565
BibTeX
@article{Garcia2025,
author = {Garcia, Joaquim Dias and Street, Alexandre and Homem-de-Mello, Tito and Muñoz, Francisco D.},
title = {Application-Driven Learning: A Closed-Loop Prediction and Optimization Approach Applied to Dynamic Reserves and Demand Forecasting},
journal = {Operations Research},
year = {2025},
volume = {73},
number = {1},
pages = {22--39},
doi = {10.1287/opre.2023.0565}
}
EUVIMED