Orateur
Description
In modern energy systems, electricity and natural gas markets are increasingly interdependent due to the prominent role of gas-fired power generation, which provides essential flexibility to balance the variability of renewable energy sources.
In such a context, this work presents a tri-level optimization model to address the optimal bidding problem faced by a price-maker electricity producer participating in both the day-ahead electricity and gas markets.
The producer, operating a diversified generation portfolio that includes gas-fired units, engages in both markets by purchasing natural gas as a fuel input and selling electricity across various generation technologies.
The upper level problem models the producer’s profit-maximization strategy, while the lower levels simulate the market clearing processes for gas and electricity, respectively.
Uncertainty in key parameters - such as demand, renewable generation, and competitor behavior - is captured through a stochastic formulation of the problem.
To address the computational complexity arising from the complexity and stochastic nature of the model, we employ neural network-based surrogate models to approximate market clearing outcomes.
Preliminary findings confirm the capability of the proposed model to capture complex intermarket dynamics and support more robust bidding strategies in multi-energy environments, while ensuring computational tractability through neural network-based approximations.
