TY - GEN
T1 - Integrated Forecasting and Scheduling of Implicit Demand Response in Balancing Markets Using Inverse Optimization
AU - Vatandoust, Behzad
AU - Zad, Bashir Bakhshideh
AU - Vallée, François
AU - Toubeau, Jean François
AU - Bruninx, Kenneth
N1 - Green Open Access added to TU Delft Institutional Repository ‘You share, we take care!’ – Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.
PY - 2023
Y1 - 2023
N2 - Demand Response (DR) programs offer flexibility that is considered to hold significant potential for enhancing power system reliability and promoting the integration of renewable energy sources. Nevertheless, the distributed nature of DR resources presents challenges in developing scalable optimization tools. This paper explores a novel data-driven approach in which DR resources are modeled through their aggregate forecasts using Inverse Optimization. The proposed method utilizes historical price-consumption data to deduce DR price-response behavior via a flexibility curve. The model is assessed within the Belgian single imbalance market context, where a Balance Responsible Party (BRP) employs the inferred flexibility curve to optimize its strategic imbalance positions by managing DR resources through suitable real-time price signals. The accuracy of the estimated flexibility provided by the proposed algorithm is evaluated by comparing it with the XGboost method. The results demonstrate that the model can effectively capture DR behavior and generate profit from providing balancing energy.
AB - Demand Response (DR) programs offer flexibility that is considered to hold significant potential for enhancing power system reliability and promoting the integration of renewable energy sources. Nevertheless, the distributed nature of DR resources presents challenges in developing scalable optimization tools. This paper explores a novel data-driven approach in which DR resources are modeled through their aggregate forecasts using Inverse Optimization. The proposed method utilizes historical price-consumption data to deduce DR price-response behavior via a flexibility curve. The model is assessed within the Belgian single imbalance market context, where a Balance Responsible Party (BRP) employs the inferred flexibility curve to optimize its strategic imbalance positions by managing DR resources through suitable real-time price signals. The accuracy of the estimated flexibility provided by the proposed algorithm is evaluated by comparing it with the XGboost method. The results demonstrate that the model can effectively capture DR behavior and generate profit from providing balancing energy.
KW - Implicit demand response
KW - Inverse Optimization
KW - Short-term Forecasting
KW - Single Imbalance Market
UR - http://www.scopus.com/inward/record.url?scp=85165228248&partnerID=8YFLogxK
U2 - 10.1109/EEM58374.2023.10161818
DO - 10.1109/EEM58374.2023.10161818
M3 - Conference contribution
AN - SCOPUS:85165228248
T3 - International Conference on the European Energy Market, EEM
BT - 2023 19th International Conference on the European Energy Market, EEM 2023
PB - IEEE
T2 - 19th International Conference on the European Energy Market, EEM 2023
Y2 - 6 June 2023 through 8 June 2023
ER -
